Organize my project

.gitignore

@@ -1,162 +1,104 @@
-# ---> Python
+# -----------------------------
-# Byte-compiled / optimized / DLL files
+# OS 기본 파일
+# -----------------------------
+.DS_Store
+Thumbs.db
+
+# -----------------------------
+# Python 환경
+# -----------------------------
 __pycache__/
-*.py[cod]
+*.pyc
-*$py.class
+*.pyo
-
+*.pyd
-# C extensions
 *.so
 
-# Distribution / packaging
+# 가상환경
-.Python
+env/
-build/
+venv/
-develop-eggs/
+.mipenv
-dist/
+/*.egg-info/
-downloads/
-eggs/
 .eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
 
-# PyInstaller
+# Poetry / pipenv
-#  Usually these files are written by a python script from a template
+.cache/
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+.venv/
-*.manifest
+
-*.spec
+# -----------------------------
-
+# IDE / Editor 관련
-# Installer logs
+# -----------------------------
-pip-log.txt
+.vscode/
-pip-delete-this-directory.txt
+.idea/
-
+*.swp
-# Unit test / coverage reports
+*.swo
-htmlcov/
+
-.tox/
+# -----------------------------
-.nox/
+# 데이터, 모델, 체크포인트
-.coverage
+# -----------------------------
-.coverage.*
+# 모델 파일
-.cache
+*.pt
-nosetests.xml
+*.pth
-coverage.xml
+*.ckpt
-*.cover
+*.onnx
-*.py,cover
+*.trt
-.hypothesis/
+*.pb
-.pytest_cache/
+*.h5
-cover/
+
-
+# 학습 관련 출력
-# Translations
+runs/
-*.mo
+logs/
-*.pot
+tensorboard/
+lightning_logs/
+checkpoint/
+checkpoints/
+
+# 데이터셋 (원하면 제외 가능)
+data/
+dataset/
+datasets/
+
+# 결과물 (이미지/비디오/추론 결과)
+outputs/
+results/
+inference/
+*.jpg
+*.png
+*.jpeg
+*.bmp
+*.mp4
+*.avi
+
+# -----------------------------
+# PyTorch & HuggingFace 캐시
+# -----------------------------
+/root/.cache/torch/
+/cache/
+/.torch/
+huggingface/
+transformers/
+
+# -----------------------------
+# Jupyter 관련
+# -----------------------------
+.ipynb_checkpoints/
+*.ipynb~
+
+# -----------------------------
+# 컴파일/빌드 아티팩트
+# -----------------------------
+build/
+dist/
+*.bin
 
-# Django stuff:
+# -----------------------------
+# Temp 파일
+# -----------------------------
+tmp/
+temp/
 *.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
 
-# pipenv
+# -----------------------------
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# 환경 변수 파일
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+# -----------------------------
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
 .env
-.venv
+.env.*
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-

Paddle_ocr/PaddleOCR

@@ -0,0 +1 @@
+Subproject commit 8853b21cfea6863c9a6797f7cb8cf0da8c50d920

Paddle_ocr/inference_pgnet.py

@@ -0,0 +1,126 @@
+import argparse
+import os
+
+import cv2
+import numpy as np
+import onnxruntime
+from paddleocr.ppocr.data.imaug.operators import (E2EResizeForTest, KeepKeys,
+                                                  NormalizeImage, ToCHWImage)
+from paddleocr.ppocr.postprocess.pg_postprocess import PGPostProcess
+
+# from pgnet.chr_dct import chr_dct_list
+
+
+class PGNetPredictor:
+    def __init__(self, img_path, cpu):
+        self.img_path = img_path
+        self.dict_path = "ic15_dict.txt"
+        # if not os.path.exists(self.dict_path):
+        #    with open(self.dict_path, "w") as f:
+        #        f.writelines(chr_dct_list)
+        if not cpu:
+            providers = ["CUDAExecutionProvider"]
+        else:
+            providers = ["CPUExecutionProvider"]
+        self.sess = onnxruntime.InferenceSession(
+            args.model_path, providers=providers)
+
+    def preprocess(self, img_path):
+        img = cv2.imread(img_path)
+        self.ori_im = img.copy()
+        data = {"image": img}
+        transforms = [
+            E2EResizeForTest(max_side_len=768, valid_set="totaltext"),
+            NormalizeImage(
+                scale=1.0 / 255.0,
+                mean=[0.485, 0.456, 0.406],
+                std=[0.229, 0.224, 0.225],
+                order="hwc",
+            ),
+            ToCHWImage(),
+            KeepKeys(keep_keys=["image", "shape"]),
+        ]
+        for transform in transforms:
+            data = transform(data)
+        img, shape_list = data
+        img = np.expand_dims(img, axis=0)
+        shape_list = np.expand_dims(shape_list, axis=0)
+        return img, shape_list
+
+    def predict(self, img):
+        ort_inputs = {self.sess.get_inputs()[0].name: img}
+        outputs = self.sess.run(None, ort_inputs)
+        preds = {}
+        preds["f_border"] = outputs[0]
+        preds["f_char"] = outputs[1]
+        preds["f_direction"] = outputs[2]
+        preds["f_score"] = outputs[3]
+        return preds
+
+    def filter_tag_det_res_only_clip(self, dt_boxes, image_shape):
+        img_height, img_width = image_shape[0:2]
+        dt_boxes_new = []
+        for box in dt_boxes:
+            box = self.clip_det_res(box, img_height, img_width)
+            dt_boxes_new.append(box)
+        dt_boxes = np.array(dt_boxes_new)
+        return dt_boxes
+
+    def clip_det_res(self, points, img_height, img_width):
+        for pno in range(points.shape[0]):
+            points[pno, 0] = int(min(max(points[pno, 0], 0), img_width - 1))
+            points[pno, 1] = int(min(max(points[pno, 1], 0), img_height - 1))
+        return points
+
+    def postprocess(self, preds, shape_list):
+        pgpostprocess = PGPostProcess(
+            character_dict_path=self.dict_path,
+            valid_set="totaltext",
+            score_thresh=0.5,
+            mode="fast",
+        )
+        post_result = pgpostprocess(preds, shape_list)
+        points, strs = post_result["points"], post_result["texts"]
+        dt_boxes = self.filter_tag_det_res_only_clip(points, self.ori_im.shape)
+        return dt_boxes, strs
+
+    def __call__(self):
+        img, shape_list = self.preprocess(self.img_path)
+        preds = self.predict(img)
+        dt_boxes, strs = self.postprocess(preds, shape_list)
+        return dt_boxes, strs
+
+    def draw(self, dt_boxes, strs, img_path):
+        src_im = cv2.imread(img_path)
+        width, height, _ = src_im.shape
+        for box, str in zip(dt_boxes, strs):
+            box = box.astype(np.int32).reshape((-1, 1, 2))
+            cv2.polylines(src_im, [box], True, color=(
+                255, 255, 0), thickness=2)
+            cv2.putText(
+                src_im,
+                str,
+                org=(int(box[0, 0, 0]), int(box[0, 0, 1])),
+                fontFace=cv2.FONT_HERSHEY_COMPLEX,
+                fontScale=0.7 / 500 * width / 2,
+                color=(0, 255, 0),
+                thickness=int(1 / 1000 * width),
+            )
+        img_out_name = os.path.basename(img_path).split(".")[0]
+        img_out_name = f"{img_out_name}_pgnet.jpg"
+        cv2.imwrite(img_out_name, src_im)
+        return src_im
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="PGPNET inference")
+    parser.add_argument("model_path", type=str, help="onnxmodel path")
+    parser.add_argument("img_path", type=str, help="image path")
+    parser.add_argument(
+        "--cpu", action="store_true", help="cpu inference, default device is gpu"
+    )
+    args = parser.parse_args()
+    pgnetpredictor = PGNetPredictor(args.img_path, args.cpu)
+    dt_boxes, strs = pgnetpredictor()
+    print(f"Predict string:{strs}")
+    pgnetpredictor.draw(dt_boxes, strs, args.img_path)

Paddle_ocr/requirements.txt

@@ -0,0 +1,2 @@
+onnxruntime-gpu
+paddleocr

Paddle_ocr/video_pgnet_infer.py

@@ -0,0 +1,127 @@
+import argparse
+import os
+import cv2
+import numpy as np
+import onnxruntime
+from paddleocr.ppocr.data.imaug.operators import (
+    E2EResizeForTest, KeepKeys, NormalizeImage, ToCHWImage
+)
+# from ppocr.data.imaug.operators import (
+#     E2EResizeForTest, KeepKeys, NormalizeImage, ToCHWImage
+# )
+from paddleocr.ppocr.postprocess.pg_postprocess import PGPostProcess
+# from ppocr.postprocess.pg_postprocess import PGPostProcess
+from pgnet.chr_dct import chr_dct_list
+
+
+class PGNetPredictor:
+    def __init__(self, model_path, cpu=False):
+        self.model_path = model_path
+        self.dict_path = "ic15_dict.txt"
+
+        if not os.path.exists(self.dict_path):
+            with open(self.dict_path, "w") as f:
+                f.writelines(chr_dct_list)
+
+        providers = ["CPUExecutionProvider"] if cpu else ["CUDAExecutionProvider"]
+        self.sess = onnxruntime.InferenceSession(model_path, providers=providers)
+
+        self.transforms = [
+            E2EResizeForTest(max_side_len=768, valid_set="totaltext"),
+            NormalizeImage(scale=1/255.0, mean=[0.485,0.456,0.406],
+                           std=[0.229,0.224,0.225], order="hwc"),
+            ToCHWImage(),
+            KeepKeys(keep_keys=["image", "shape"]),
+        ]
+
+        self.pgpostprocess = PGPostProcess(
+            character_dict_path=self.dict_path,
+            valid_set="totaltext",
+            score_thresh=0.5,
+            mode="fast",
+        )
+
+    def preprocess(self, img):
+        self.ori_im = img.copy()
+        data = {"image": img}
+
+        for transform in self.transforms:
+            data = transform(data)
+
+        img, shape_list = data
+        return np.expand_dims(img, axis=0), np.expand_dims(shape_list, axis=0)
+
+    def predict(self, img):
+        ort_inputs = {self.sess.get_inputs()[0].name: img}
+        outputs = self.sess.run(None, ort_inputs)
+
+        return {
+            "f_border": outputs[0],
+            "f_char": outputs[1],
+            "f_direction": outputs[2],
+            "f_score": outputs[3],
+        }
+
+    def clip_boxes(self, boxes, shape):
+        h, w = shape[:2]
+        clipped = []
+        for box in boxes:
+            box[:, 0] = np.clip(box[:, 0], 0, w - 1)
+            box[:, 1] = np.clip(box[:, 1], 0, h - 1)
+            clipped.append(box)
+        return np.array(clipped)
+
+    def postprocess(self, preds, shape_list):
+        result = self.pgpostprocess(preds, shape_list)
+        pts, texts = result["points"], result["texts"]
+        return self.clip_boxes(pts, self.ori_im.shape), texts
+
+    def infer(self, img):
+        img_input, shape = self.preprocess(img)
+        preds = self.predict(img_input)
+        return self.postprocess(preds, shape)
+
+
+def draw_results(frame, boxes, texts):
+    for box, text in zip(boxes, texts):
+        box = box.astype(int).reshape(-1, 1, 2)
+        cv2.polylines(frame, [box], True, (255,255,0), 2)
+        cv2.putText(frame, text, tuple(box[0][0]), cv2.FONT_HERSHEY_SIMPLEX, 
+                    0.7, (0,255,0), 2)
+    return frame
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="PGNet Video OCR")
+    parser.add_argument("--model", type=str, required=True)
+    parser.add_argument("--video", type=str, required=True)
+    parser.add_argument("--cpu", action="store_true")
+    args = parser.parse_args()
+
+    predictor = PGNetPredictor(args.model, args.cpu)
+
+    cap = cv2.VideoCapture(args.video)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    fps = cap.get(cv2.CAP_PROP_FPS)
+
+    out_name = os.path.splitext(os.path.basename(args.video))[0] + "_pgnet_output.mp4"
+    out_path = os.path.join(os.path.dirname(args.video), out_name)
+
+    writer = cv2.VideoWriter(out_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
+
+    print(f"▶ Processing video... (Output: {out_path})")
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        boxes, texts = predictor.infer(frame)
+        frame = draw_results(frame, boxes, texts)
+        writer.write(frame)
+
+    cap.release()
+    writer.release()
+
+    print("🎉 Done! Video saved:", out_path)

YOLO_FACE_EXP/dataset.py

@@ -0,0 +1,39 @@
+import torch
+from torchvision import datasets, transforms
+from torch.utils.data import DataLoader
+import os
+
+def get_face_dataloaders(data_dir, batch_size=64, num_workers=4):
+    """
+    Input: data_dir (e.g., ~/face_exp/datasets)
+    Structure assumed: data_dir/CASIA-WebFace/ID/images.jpg
+    """
+    
+    # 1. Train Transform (Augmentation + Resize to 128x128)
+    train_transform = transforms.Compose([
+        transforms.Resize((128, 128), interpolation=transforms.InterpolationMode.BICUBIC),
+        transforms.RandomHorizontalFlip(p=0.5),
+        transforms.ColorJitter(brightness=0.1, contrast=0.1, saturation=0.1),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+    ])
+
+    # 2. Path Setup
+    train_dir = os.path.join(data_dir, 'CASIA-WebFace')
+    
+    if not os.path.exists(train_dir):
+        raise FileNotFoundError(f"데이터셋 경로를 찾을 수 없습니다: {train_dir}\n'CASIA-WebFace' 폴더가 해당 위치에 있는지 확인해주세요.")
+
+    # 3. Dataset & Loader
+    train_dataset = datasets.ImageFolder(root=train_dir, transform=train_transform)
+    
+    train_loader = DataLoader(
+        train_dataset,
+        batch_size=batch_size,
+        shuffle=True,
+        num_workers=num_workers,
+        pin_memory=True,
+        drop_last=True 
+    )
+
+    return train_loader, len(train_dataset.classes)

YOLO_FACE_EXP/export_onnx.py

@@ -0,0 +1,71 @@
+import torch
+import argparse
+import os
+from model import get_face_model
+
+def export_to_onnx(pt_path, output_path):
+    print(f"🔄 Loading model from: {pt_path}")
+
+    # 1. 모델 구조 불러오기 및 가중치 로드
+    # 보드용 모델이므로 학습용 ArcFace 헤더는 버리고, Backbone만 가져옵니다.
+    model = get_face_model()
+    
+    # CPU로 로드 (변환은 굳이 GPU 불필요)
+    checkpoint = torch.load(pt_path, map_location='cpu')
+    
+    # state_dict 로드 (혹시 모를 키 불일치 방지를 위해 strict=False는 선택사항이나, 여기선 구조가 같으므로 True 권장)
+    try:
+        model.load_state_dict(checkpoint)
+    except RuntimeError as e:
+        print(f"⚠️ Key mismatch detected. Trying to load with strict=False...")
+        model.load_state_dict(checkpoint, strict=False)
+
+    # 2. Eval 모드 전환 (매우 중요)
+    # 이걸 안 하면 BatchNorm, Dropout 등이pip  학습 모드로 동작하여 결과가 이상해집니다.
+    model.eval()
+
+    # 3. Dummy Input 생성 (Static Shape: 128x128)
+    # 보드 사양에 맞춰 배치 사이즈는 1로 고정합니다. [1, 3, 128, 128]
+    dummy_input = torch.randn(1, 3, 128, 128)
+
+    print(f"Target ONNX Path: {output_path}")
+
+    # 4. ONNX Export
+    # external_data=False는 PyTorch export에서 기본적으로 2GB 미만 모델에 대해 적용되어 단일 파일로 나옵니다.
+    # dynamic_axes 옵션을 뺌으로써 Static Shape을 강제합니다.
+    torch.onnx.export(
+        model,                      # 실행될 모델
+        dummy_input,                # 모델 입력값 (차원 체크용)
+        output_path,                # 저장될 경로
+        # export_params=True,         # 모델 파일 안에 웨이트 저장 (external_data=False 효과)
+        # opset_version=11,           # 임베디드 보드에서 가장 호환성 좋은 버전 (11 추천)
+        # do_constant_folding=True,   # 상수 폴딩 최적화
+        input_names=['input'],      # 입력 노드 이름
+        output_names=['output'],     # 출력 노드 이름
+        external_data=False
+        # dynamic_axes={...}  <-- 이 옵션을 사용하지 않음으로써 Static Shape으로 고정됨!
+    )
+
+    print(f"✅ Conversion Completed! Model saved at: {output_path}")
+    print(f"ℹ️  Input Shape: {dummy_input.shape} (Static)")
+    print(f"ℹ️  Please check if '{output_path}' is a single file.")
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Convert PyTorch model to ONNX')
+    
+    # 입력받을 .pt 파일 경로
+    parser.add_argument('--input', type=str, required=True, help='Input .pt file path')
+    
+    # 출력할 .onnx 파일 경로 (옵션)
+    parser.add_argument('--output', type=str, default=None, help='Output .onnx file path')
+
+    args = parser.parse_args()
+
+    # Output 경로가 없으면 Input 경로에서 확장자만 바꿔서 자동 지정
+    if args.output is None:
+        args.output = args.input.replace('.pt', '.onnx')
+
+    if not os.path.exists(args.input):
+        print(f"❌ Error: Input file not found: {args.input}")
+    else:
+        export_to_onnx(args.input, args.output)

YOLO_FACE_EXP/model.py

@@ -0,0 +1,149 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import math
+
+# --------------------------------------------------------
+# Basic Blocks (Quantization Friendly: ReLU used)
+# --------------------------------------------------------
+def conv3x3(in_planes, out_planes, stride=1):
+    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
+                     padding=1, bias=False)
+
+class Bottleneck(nn.Module):
+    expansion = 4
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None):
+        super(Bottleneck, self).__init__()
+        # Kernel size restricted to 1 and 3 for board compatibility
+        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False)
+        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
+        # self.relu = nn.ReLU(inplace=True) # PReLU -> ReLU
+        self.relu = nn.ReLU(inplace=False) # PReLU -> ReLU
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        residual = x
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+        out = self.conv2(out)
+        out = self.bn2(out)
+        out = self.relu(out)
+        out = self.conv3(out)
+        out = self.bn3(out)
+        if self.downsample is not None:
+            residual = self.downsample(x)
+        out += residual
+        out = self.relu(out)
+        return out
+
+# --------------------------------------------------------
+# Backbone: Modified ResNet-50
+# --------------------------------------------------------
+class ResNetFace(nn.Module):
+    def __init__(self, block, layers, embedding_size=128):
+        super(ResNetFace, self).__init__()
+        self.inplanes = 64
+        
+        # Stem Block: 7x7 replaced by three 3x3 convs
+        self.stem = nn.Sequential(
+            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(64),
+            # nn.ReLU(inplace=True),
+            nn.ReLU(inplace=False),
+            nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(64),
+            # nn.ReLU(inplace=True),
+            nn.ReLU(inplace=False),
+            nn.Conv2d(64, 64, kernel_size=3, stride=2, padding=1, bias=False),
+            nn.BatchNorm2d(64),
+            # nn.ReLU(inplace=True),
+            nn.ReLU(inplace=False),
+        )
+        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+
+        self.layer1 = self._make_layer(block, 64, layers[0])
+        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
+        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
+        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
+        
+        # Output Head: 128x128 Input -> 4x4 Feature Map
+        self.avgpool = nn.AvgPool2d(4) # Result: 1x1
+        
+        # FC layer replaced by 1x1 Conv for 128-d embedding
+        self.fc_conv = nn.Conv2d(512 * block.expansion, embedding_size, kernel_size=1, bias=False)
+        self.bn_last = nn.BatchNorm2d(embedding_size)
+
+        # Init weights
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+            elif isinstance(m, nn.BatchNorm2d):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+
+    def _make_layer(self, block, planes, blocks, stride=1):
+        downsample = None
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = nn.Sequential(
+                nn.Conv2d(self.inplanes, planes * block.expansion,
+                          kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(planes * block.expansion),
+            )
+        layers = []
+        layers.append(block(self.inplanes, planes, stride, downsample))
+        self.inplanes = planes * block.expansion
+        for _ in range(1, blocks):
+            layers.append(block(self.inplanes, planes))
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        x = self.stem(x)
+        x = self.maxpool(x)
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+        x = self.layer4(x)
+        x = self.avgpool(x)
+        x = self.fc_conv(x)
+        x = self.bn_last(x) # Output: [N, 128, 1, 1]
+        return x
+
+# --------------------------------------------------------
+# ArcFace Loss Header
+# --------------------------------------------------------
+class ArcFace(nn.Module):
+    def __init__(self, in_features, out_features, s=64.0, m=0.50):
+        super(ArcFace, self).__init__()
+        self.in_features = in_features
+        self.out_features = out_features
+        self.s = s
+        self.m = m
+        self.weight = nn.Parameter(torch.FloatTensor(out_features, in_features))
+        nn.init.xavier_uniform_(self.weight)
+
+    def forward(self, input, label):
+        # Flatten [N, 128, 1, 1] -> [N, 128] for loss calculation
+        embedding = input.view(input.size(0), -1)
+        
+        cosine = F.linear(F.normalize(embedding), F.normalize(self.weight))
+        
+        # Stable implementation of ArcFace
+        theta = torch.acos(torch.clamp(cosine, -1.0 + 1e-7, 1.0 - 1e-7))
+        target_logits = torch.cos(theta + self.m)
+        
+        one_hot = torch.zeros_like(cosine)
+        one_hot.scatter_(1, label.view(-1, 1).long(), 1)
+        
+        output = one_hot * target_logits + (1.0 - one_hot) * cosine
+        output *= self.s
+        return output
+
+def get_face_model():
+    return ResNetFace(Bottleneck, [3, 4, 6, 3], embedding_size=128)

YOLO_FACE_EXP/train_ver1.py

@@ -0,0 +1,120 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import os
+import argparse
+from tqdm import tqdm
+from datetime import datetime  # 시간 정보를 가져오기 위해 추가
+
+# Import our custom modules
+from model import get_face_model, ArcFace
+from dataset import get_face_dataloaders
+
+def main():
+    # --------------------------------------------------------
+    # 1. Hyperparameters & Settings
+    # --------------------------------------------------------
+    parser = argparse.ArgumentParser(description='Face Recognition Training for Apache 6')
+    
+    # 데이터셋 경로 (사용자 환경에 맞게 기본값 설정)
+    parser.add_argument('--data_dir', type=str, default='/home/cuuva/face_exp/datasets', help='Path to datasets')
+    
+    # 결과 저장 최상위 경로 (여기 아래에 시간별 폴더가 생김)
+    parser.add_argument('--project_dir', type=str, default='./results', help='Base directory for results')
+    
+    parser.add_argument('--epochs', type=int, default=20, help='Number of epochs')
+    parser.add_argument('--batch_size', type=int, default=64, help='Batch size')
+    parser.add_argument('--lr', type=float, default=0.1, help='Learning rate')
+    
+    args = parser.parse_args()
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    print(f"Device: {device}")
+
+    # --------------------------------------------------------
+    # [수정됨] 실험 디렉토리 생성 로직 (yy-mm-dd-hour-minute)
+    # --------------------------------------------------------
+    # 현재 시간 구하기
+    current_time = datetime.now().strftime("%y-%m-%d-%H-%M")
+    
+    # 최종 저장 경로: ./results/23-12-12-15-30/
+    save_dir = os.path.join(args.project_dir, current_time)
+    
+    # 폴더 생성
+    os.makedirs(save_dir, exist_ok=True)
+    print(f"✅ Experiment results will be saved to: {save_dir}")
+
+    # --------------------------------------------------------
+    # 2. Load Data
+    # --------------------------------------------------------
+    print("Loading Data...")
+    try:
+        train_loader, num_classes = get_face_dataloaders(args.data_dir, args.batch_size)
+        print(f"Classes (People): {num_classes}, Batch Size: {args.batch_size}")
+    except Exception as e:
+        print(f"❌ Error loading data: {e}")
+        return
+
+    # --------------------------------------------------------
+    # 3. Initialize Model & Loss
+    # --------------------------------------------------------
+    # Backbone (보드에 배포할 모델)
+    backbone = get_face_model().to(device)
+    
+    # ArcFace Header (학습용 Loss 계산기)
+    metric_fc = ArcFace(in_features=128, out_features=num_classes).to(device)
+
+    # Loss
+    criterion = nn.CrossEntropyLoss()
+
+    # Optimizer
+    optimizer = optim.SGD([
+        {'params': backbone.parameters()},
+        {'params': metric_fc.parameters()}
+    ], lr=args.lr, momentum=0.9, weight_decay=5e-4)
+
+    # Scheduler
+    scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=[8, 14, 18], gamma=0.1)
+
+    # --------------------------------------------------------
+    # 4. Training Loop
+    # --------------------------------------------------------
+    print("🚀 Start Training...")
+    
+    for epoch in range(args.epochs):
+        backbone.train()
+        metric_fc.train()
+        
+        running_loss = 0.0
+        pbar = tqdm(train_loader, desc=f"Epoch {epoch+1}/{args.epochs}")
+        
+        for images, labels in pbar:
+            images, labels = images.to(device), labels.to(device)
+
+            optimizer.zero_grad()
+
+            # Forward Pass
+            features = backbone(images)       # [N, 128, 1, 1]
+            outputs = metric_fc(features, labels) # [N, Num_Classes]
+
+            # Loss Calc & Backward
+            loss = criterion(outputs, labels)
+            loss.backward()
+            optimizer.step()
+
+            running_loss += loss.item()
+            pbar.set_postfix({'loss': running_loss / (pbar.n + 1)})
+
+        scheduler.step()
+        
+        # [수정됨] Save Checkpoint (.pt 확장자 사용)
+        # 해당 실험 폴더(save_dir) 안에 저장됨
+        save_path = os.path.join(save_dir, f"backbone_epoch_{epoch+1}.pt")
+        torch.save(backbone.state_dict(), save_path)
+        
+        # 마지막 에폭일 때 로그 출력
+        if epoch == args.epochs - 1:
+            print(f"🎉 Training Finished! Final model saved at: {save_path}")
+
+if __name__ == "__main__":
+    main()

YOLO_FACE_EXP/train_ver2.py

@@ -0,0 +1,141 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import os
+import argparse
+from tqdm import tqdm
+from datetime import datetime
+from torchvision import transforms
+from torch.utils.data import DataLoader
+
+# Import Custom Modules
+from model import get_face_model, ArcFace
+from dataset import get_face_dataloaders
+from validation import LFWDataset, validate_lfw
+
+def main():
+    # 1. Hyperparameters
+    parser = argparse.ArgumentParser(description='Face Recognition Training with LFW Validation')
+    parser.add_argument('--data_dir', type=str, default='/home/cuuva/face_exp/datasets', help='Root dataset dir')
+    parser.add_argument('--project_dir', type=str, default='./results', help='Save dir')
+    parser.add_argument('--epochs', type=int, default=20)
+    parser.add_argument('--batch_size', type=int, default=64)
+    parser.add_argument('--lr', type=float, default=0.1)
+    args = parser.parse_args()
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    print(f"Device: {device}")
+
+    # 디렉토리 설정
+    current_time = datetime.now().strftime("%y-%m-%d-%H-%M")
+    base_save_dir = os.path.join(args.project_dir, current_time)
+    best_save_dir = os.path.join(base_save_dir, 'best_model')
+    os.makedirs(best_save_dir, exist_ok=True)
+    
+    print(f"✅ Save path: {base_save_dir}")
+
+    # 2. Train Data Loader
+    print("Loading Train Data...")
+    try:
+        train_loader, num_classes = get_face_dataloaders(args.data_dir, args.batch_size)
+    except Exception as e:
+        print(f"❌ Train Data Error: {e}")
+        return
+
+    # --------------------------------------------------------
+    # [수정됨] 3. LFW Validation Loader (경로 로직 개선)
+    # --------------------------------------------------------
+    print("Loading LFW Data...")
+    
+    # pairs.txt가 있는 루트 경로: ~/face_exp/datasets/LFW
+    lfw_root = os.path.join(args.data_dir, 'LFW')
+    pairs_path = os.path.join(lfw_root, 'pairs.txt') 
+
+    # 실제 이미지가 있는 경로 찾기
+    # 1순위: ~/face_exp/datasets/LFW/lfw (보여주신 구조)
+    # 2순위: ~/face_exp/datasets/LFW (일반적인 구조)
+    if os.path.exists(os.path.join(lfw_root, 'lfw')):
+        lfw_img_dir = os.path.join(lfw_root, 'lfw')
+    else:
+        lfw_img_dir = lfw_root
+    
+    print(f"ℹ️  Pairs path: {pairs_path}")
+    print(f"ℹ️  Images path: {lfw_img_dir}")
+
+    if os.path.exists(pairs_path) and os.path.exists(lfw_img_dir):
+        lfw_transform = transforms.Compose([
+            transforms.Resize((128, 128), interpolation=transforms.InterpolationMode.BICUBIC),
+            transforms.ToTensor(),
+            transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+        ])
+        
+        # 여기서 lfw_img_dir를 넘겨주는 것이 핵심!
+        lfw_dataset = LFWDataset(lfw_img_dir, pairs_path, transform=lfw_transform)
+        
+        lfw_loader = DataLoader(lfw_dataset, batch_size=64, shuffle=False, num_workers=4, drop_last=False)
+        do_validation = True
+        print(f"✅ LFW Loaded. Pairs: {len(lfw_dataset)}")
+    else:
+        print(f"⚠️ Warning: 'pairs.txt' or Image dir not found. Skipping Validation.")
+        do_validation = False
+
+    # 4. Model & Loss
+    backbone = get_face_model().to(device)
+    metric_fc = ArcFace(in_features=128, out_features=num_classes).to(device)
+    criterion = nn.CrossEntropyLoss()
+    
+    optimizer = optim.SGD([
+        {'params': backbone.parameters()},
+        {'params': metric_fc.parameters()}
+    ], lr=args.lr, momentum=0.9, weight_decay=5e-4)
+    
+    scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=[8, 14, 18], gamma=0.1)
+
+    # 5. Training Loop
+    print("🚀 Start Training...")
+    
+    best_acc = 0.0 
+
+    for epoch in range(args.epochs):
+        # --- TRAIN ---
+        backbone.train()
+        metric_fc.train()
+        
+        running_loss = 0.0
+        pbar = tqdm(train_loader, desc=f"Epoch {epoch+1}/{args.epochs}")
+        
+        for images, labels in pbar:
+            images, labels = images.to(device), labels.to(device)
+            optimizer.zero_grad()
+            
+            features = backbone(images)
+            outputs = metric_fc(features, labels)
+            loss = criterion(outputs, labels)
+            loss.backward()
+            optimizer.step()
+            
+            running_loss += loss.item()
+            pbar.set_postfix({'loss': f"{running_loss / (pbar.n + 1):.4f}"})
+        
+        scheduler.step()
+
+        # --- VALIDATION (LFW) ---
+        if do_validation:
+            acc, th = validate_lfw(backbone, lfw_loader, device)
+            print(f"📊 LFW Acc: {acc*100:.2f}% (Threshold: {th:.2f})")
+            
+            if acc > best_acc:
+                best_acc = acc
+                save_path = os.path.join(best_save_dir, "best_backbone.pt")
+                torch.save(backbone.state_dict(), save_path)
+                print(f"🏆 Best Model Updated! Saved to {save_path}")
+        else:
+            save_path = os.path.join(base_save_dir, f"backbone_epoch_{epoch+1}.pt")
+            torch.save(backbone.state_dict(), save_path)
+
+        torch.save(backbone.state_dict(), os.path.join(base_save_dir, "last_backbone.pt"))
+
+    print("\n🎉 Training Finished!")
+
+if __name__ == "__main__":
+    main()

YOLO_FACE_EXP/validation.py

@@ -0,0 +1,119 @@
+import torch
+import torch.nn.functional as F
+from torch.utils.data import Dataset, DataLoader
+from torchvision import transforms
+from PIL import Image
+import os
+import numpy as np
+
+# --------------------------------------------------------
+# 1. LFW Dataset Loader
+# --------------------------------------------------------
+class LFWDataset(Dataset):
+    def __init__(self, lfw_dir, pairs_path, transform=None):
+        self.lfw_dir = lfw_dir
+        self.pairs_path = pairs_path
+        self.transform = transform
+        self.validation_images = self.get_lfw_paths(lfw_dir)
+
+    def get_lfw_paths(self, lfw_dir):
+        # pairs.txt 파싱하여 이미지 경로 쌍과 정답(issame) 리스트 생성
+        pairs = []
+        with open(self.pairs_path, 'r') as f:
+            lines = f.readlines()[1:] # 첫 줄(헤더) 건너뜀
+            
+        for line in lines:
+            p = line.strip().split('\t')
+            
+            if len(p) == 3: # 같은 사람 (name, img1_num, img2_num)
+                name = p[0]
+                img1 = os.path.join(lfw_dir, name, f"{name}_{int(p[1]):04d}.jpg")
+                img2 = os.path.join(lfw_dir, name, f"{name}_{int(p[2]):04d}.jpg")
+                issame = True
+                pairs.append((img1, img2, issame))
+                
+            elif len(p) == 4: # 다른 사람 (name1, img1_num, name2, img2_num)
+                name1 = p[0]
+                img1 = os.path.join(lfw_dir, name1, f"{name1}_{int(p[1]):04d}.jpg")
+                name2 = p[2]
+                img2 = os.path.join(lfw_dir, name2, f"{name2}_{int(p[3]):04d}.jpg")
+                issame = False
+                pairs.append((img1, img2, issame))
+        return pairs
+
+    def __len__(self):
+        return len(self.validation_images)
+
+    def __getitem__(self, index):
+        img1_path, img2_path, issame = self.validation_images[index]
+        
+        try:
+            img1 = Image.open(img1_path).convert('RGB')
+            img2 = Image.open(img2_path).convert('RGB')
+        except Exception as e:
+            # 혹시 파일이 없을 경우를 대비한 더미 (실제론 파일 확인 필요)
+            print(f"File Load Error: {e}")
+            img1 = Image.new('RGB', (128, 128))
+            img2 = Image.new('RGB', (128, 128))
+        
+        if self.transform:
+            img1 = self.transform(img1)
+            img2 = self.transform(img2)
+            
+        return img1, img2, issame
+
+# --------------------------------------------------------
+# 2. Evaluation Function
+# --------------------------------------------------------
+def validate_lfw(model, lfw_loader, device):
+    model.eval()
+    similarities = []
+    actual_issame = []
+
+    print("🔍 Validating on LFW...")
+    with torch.no_grad():
+        for img1, img2, issame in lfw_loader:
+            img1, img2 = img1.to(device), img2.to(device)
+            
+            # Feature Extraction
+            feat1 = model(img1) # [B, 128, 1, 1]
+            feat2 = model(img2) # [B, 128, 1, 1]
+            
+            # Flatten
+            feat1 = feat1.view(feat1.size(0), -1)
+            feat2 = feat2.view(feat2.size(0), -1)
+            
+            # Cosine Similarity Calculation
+            # 128차원 벡터의 코사인 유사도 (-1 ~ 1)
+            cos_sim = F.cosine_similarity(feat1, feat2)
+            
+            similarities.extend(cos_sim.cpu().numpy())
+            actual_issame.extend(issame.numpy())
+
+    similarities = np.array(similarities)
+    actual_issame = np.array(actual_issame)
+
+    # ----------------------------------------------------
+    # Best Threshold Search (단순화된 버전)
+    # ----------------------------------------------------
+    best_acc = 0.0
+    best_th = 0.0
+    
+    # -1.0 부터 1.0 까지 0.01 단위로 Threshold를 이동하며 정확도 측정
+    thresholds = np.arange(-1.0, 1.0, 0.01)
+    
+    for th in thresholds:
+        # th보다 크면 True(동일인), 작으면 False(타인) 예측
+        predict_issame = np.greater(similarities, th)
+        
+        # 정답과 비교
+        true_positives = np.sum(np.logical_and(predict_issame, actual_issame))
+        true_negatives = np.sum(np.logical_and(np.logical_not(predict_issame), np.logical_not(actual_issame)))
+        
+        acc = (true_positives + true_negatives) / len(actual_issame)
+        
+        if acc > best_acc:
+            best_acc = acc
+            best_th = th
+
+    return best_acc, best_th

coco5class_exp/coco5class.yaml

@@ -0,0 +1,9 @@
+# path: /home/cuuva/experiment/datasets/VisDrone  # 데이터 경로
+train: /home/cuuva/experiment/datasets/coco5class/images/train
+val: /home/cuuva/experiment/datasets/coco5class/images/val
+test: /home/cuuva/experiment/datasets/coco5class/images/test
+
+# nc: 7
+nc: 5
+
+names: ['person','car', 'truck', 'bus', 'motor']

coco5class_exp/coco5class_exp.ipynb

@@ -0,0 +1,342 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "6b410dab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from ultralytics import YOLO\n",
+    "\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f66929b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "torch.cuda.is_available()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e5e2ab7b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "🔍 Checking split: train  (files: 117266)\n",
+      "\n",
+      "🔍 Checking split: val  (files: 4952)\n",
+      "\n",
+      "📌 클래스 통계 결과:\n",
+      " - Class 0: 268029 개\n",
+      " - Class 1: 45449 개\n",
+      " - Class 2: 10384 개\n",
+      " - Class 3: 6344 개\n",
+      " - Class 4: 9021 개\n",
+      "\n",
+      "총 클래스 종류: 5\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from collections import Counter\n",
+    "\n",
+    "label_root = \"/home/cuuva/experiment/datasets/coco5class/labels\"\n",
+    "splits = [\"train\", \"val\"]\n",
+    "\n",
+    "class_counter = Counter()\n",
+    "\n",
+    "for split in splits:\n",
+    "    split_path = os.path.join(label_root, split)\n",
+    "    \n",
+    "    # 라벨 txt 파일 탐색\n",
+    "    label_files = [f for f in os.listdir(split_path) if f.endswith(\".txt\")]\n",
+    "    \n",
+    "    print(f\"\\n🔍 Checking split: {split}  (files: {len(label_files)})\")\n",
+    "\n",
+    "    for file in label_files:\n",
+    "        file_path = os.path.join(split_path, file)\n",
+    "        with open(file_path, \"r\") as f:\n",
+    "            for line in f.readlines():\n",
+    "                if line.strip():  # 빈 줄 제거\n",
+    "                    class_id = line.split()[0]  # 첫번째 값 = 클래스\n",
+    "                    class_counter[class_id] += 1\n",
+    "\n",
+    "# 최종 결과 출력\n",
+    "print(\"\\n📌 클래스 통계 결과:\")\n",
+    "for cls, count in sorted(class_counter.items(), key=lambda x: int(x[0])):\n",
+    "    print(f\" - Class {cls}: {count} 개\")\n",
+    "\n",
+    "print(f\"\\n총 클래스 종류: {len(class_counter)}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6bb38c03",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "New https://pypi.org/project/ultralytics/8.3.235 available 😃 Update with 'pip install -U ultralytics'\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, augment=False, auto_augment=randaugment, batch=-1, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=/home/cuuva/experiment/coco5class_exp/coco5class.yaml, degrees=0.0, deterministic=True, device=0, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, epochs=300, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.001, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolov8m.pt, momentum=0.937, mosaic=1.0, multi_scale=False, name=5class, nbs=64, nms=False, opset=None, optimize=False, optimizer=AdamW, overlap_mask=True, patience=40, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=coco5class_v8m, rect=False, resume=False, retina_masks=False, save=True, save_conf=False, save_crop=False, save_dir=/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n",
+      "Overriding model.yaml nc=80 with nc=5\n",
+      "\n",
+      "                   from  n    params  module                                       arguments                     \n",
+      "  0                  -1  1      1392  ultralytics.nn.modules.conv.Conv             [3, 48, 3, 2]                 \n",
+      "  1                  -1  1     41664  ultralytics.nn.modules.conv.Conv             [48, 96, 3, 2]                \n",
+      "  2                  -1  2    111360  ultralytics.nn.modules.block.C2f             [96, 96, 2, True]             \n",
+      "  3                  -1  1    166272  ultralytics.nn.modules.conv.Conv             [96, 192, 3, 2]               \n",
+      "  4                  -1  4    813312  ultralytics.nn.modules.block.C2f             [192, 192, 4, True]           \n",
+      "  5                  -1  1    664320  ultralytics.nn.modules.conv.Conv             [192, 384, 3, 2]              \n",
+      "  6                  -1  4   3248640  ultralytics.nn.modules.block.C2f             [384, 384, 4, True]           \n",
+      "  7                  -1  1   1991808  ultralytics.nn.modules.conv.Conv             [384, 576, 3, 2]              \n",
+      "  8                  -1  2   3985920  ultralytics.nn.modules.block.C2f             [576, 576, 2, True]           \n",
+      "  9                  -1  1    831168  ultralytics.nn.modules.block.SPPF            [576, 576, 5]                 \n",
+      " 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 12                  -1  2   1993728  ultralytics.nn.modules.block.C2f             [960, 384, 2]                 \n",
+      " 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 15                  -1  2    517632  ultralytics.nn.modules.block.C2f             [576, 192, 2]                 \n",
+      " 16                  -1  1    332160  ultralytics.nn.modules.conv.Conv             [192, 192, 3, 2]              \n",
+      " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 18                  -1  2   1846272  ultralytics.nn.modules.block.C2f             [576, 384, 2]                 \n",
+      " 19                  -1  1   1327872  ultralytics.nn.modules.conv.Conv             [384, 384, 3, 2]              \n",
+      " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 21                  -1  2   4207104  ultralytics.nn.modules.block.C2f             [960, 576, 2]                 \n",
+      " 22        [15, 18, 21]  1   3778591  ultralytics.nn.modules.head.Detect           [5, [192, 384, 576]]          \n",
+      "Model summary: 169 layers, 25,859,215 parameters, 25,859,199 gradients, 79.1 GFLOPs\n",
+      "\n",
+      "Transferred 469/475 items from pretrained weights\n",
+      "Freezing layer 'model.22.dfl.conv.weight'\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 8101.9±2264.5 MB/s, size: 195.4 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/experiment/datasets/coco5class/labels/train.cache... 117266 images, 48605 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 118287/118287 192.2Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mComputing optimal batch size for imgsz=640 at 60.0% CUDA memory utilization.\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mCUDA:0 (NVIDIA GeForce RTX 5090) 31.33G total, 0.24G reserved, 0.23G allocated, 30.86G free\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/cuuva/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "      Params      GFLOPs  GPU_mem (GB)  forward (ms) backward (ms)                   input                  output\n",
+      "    25859215       79.08         2.261         30.79         146.6        (1, 3, 640, 640)                    list\n",
+      "    25859215       158.2         3.569         9.957         33.28        (2, 3, 640, 640)                    list\n",
+      "    25859215       316.3         4.731         13.44         46.58        (4, 3, 640, 640)                    list\n",
+      "    25859215       632.6         7.785         25.68         70.42        (8, 3, 640, 640)                    list\n",
+      "    25859215        1265        10.414         27.14         117.5       (16, 3, 640, 640)                    list\n",
+      "    25859215        2531        20.416         55.02         239.2       (32, 3, 640, 640)                    list\n",
+      "    25859215        5061        36.937         116.3         435.7       (64, 3, 640, 640)                    list\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mUsing batch-size 29 for CUDA:0 19.03G/31.33G (61%) ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 6524.6±3206.6 MB/s, size: 190.9 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/experiment/datasets/coco5class/labels/train.cache... 117266 images, 48605 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 118287/118287 217.1Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 4736.1±2206.1 MB/s, size: 185.8 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /home/cuuva/experiment/datasets/coco5class/labels/val.cache... 4952 images, 2049 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 5000/5000 6.6Mit/s 0.0s0s\n",
+      "Plotting labels to /home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/labels.jpg... \n",
+      "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.001, momentum=0.937) with parameter groups 77 weight(decay=0.0), 84 weight(decay=0.000453125), 83 bias(decay=0.0)\n",
+      "Image sizes 640 train, 640 val\n",
+      "Using 8 dataloader workers\n",
+      "Logging results to \u001b[1m/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class\u001b[0m\n",
+      "Starting training for 300 epochs...\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      1/300      14.1G      1.156      1.187      1.242        133        640: 100% ━━━━━━━━━━━━ 4079/4079 3.3it/s 20:20<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 8.9it/s 9.8s0.1s\n",
+      "                   all       5000      13759      0.471      0.374      0.387      0.237\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      2/300      14.1G      1.204      1.229      1.282         98        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 20:06<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 8.6it/s 10.1s0.1s\n",
+      "                   all       5000      13759      0.615      0.494       0.54      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      3/300      14.1G      1.172      1.165      1.258        120        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 20:08<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 8.9it/s 9.8s<0.2s\n",
+      "                   all       5000      13759      0.644      0.526       0.58      0.395\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      4/300      14.1G      1.127      1.088      1.231         86        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 20:06<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 9.2it/s 9.4s<0.2s\n",
+      "                   all       5000      13759      0.671      0.559      0.616      0.424\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      5/300      14.1G      1.088      1.025      1.204        107        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 20:01<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 9.3it/s 9.3s<0.1s\n",
+      "                   all       5000      13759      0.675       0.58      0.641      0.453\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      6/300      14.1G      1.057     0.9789      1.185        162        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 20:01<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 9.4it/s 9.3s<0.1s\n",
+      "                   all       5000      13759       0.71      0.575      0.656      0.467\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      7/300      14.1G      1.036     0.9461      1.172        121        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 20:01<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 9.4it/s 9.3s<0.1s\n",
+      "                   all       5000      13759      0.725      0.588      0.672       0.48\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      8/300      14.1G      1.023     0.9197      1.161        105        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 19:60<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 9.4it/s 9.2s0.1ss\n",
+      "                   all       5000      13759      0.735      0.587      0.681      0.488\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      9/300      14.1G      1.009     0.9032       1.15        136        640: 100% ━━━━━━━━━━━━ 4079/4079 3.4it/s 19:60<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 87/87 9.2it/s 9.5s<0.1s\n",
+      "                   all       5000      13759      0.719      0.603      0.683      0.493\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     10/300      14.1G     0.9986     0.8829      1.145        136        640: 82% ━━━━━━━━━╸── 3329/4079 3.4it/s 16:20<3:401"
+     ]
+    }
+   ],
+   "source": [
+    "# Load a pretrained YOLO11n model\n",
+    "model = YOLO('yolov8m.pt')\n",
+    "\n",
+    "train_results = model.train(\n",
+    "    data=\"/home/cuuva/experiment/coco5class_exp/coco5class.yaml\", #['person','car', 'truck', 'bus', 'motor']\n",
+    "    epochs=300,\n",
+    "    imgsz=640,\n",
+    "    batch=-1,\n",
+    "    device=\"cuda\",\n",
+    "    optimizer = 'AdamW',\n",
+    "    lr0 = 0.001,\n",
+    "    patience = 40,\n",
+    "    project = 'coco5class_v8m',\n",
+    "    name = '5class',\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c87a7d82",
+   "metadata": {},
+   "source": [
+    "'''\n",
+    "\n",
+    "all : 0.559\n",
+    "\n",
+    "person : 0.615\n",
+    "\n",
+    "car : 0.496\n",
+    "\n",
+    "truck : 0.438\n",
+    "\n",
+    "bus : 0.739\n",
+    "\n",
+    "motor : 0.509\n",
+    "\n",
+    "'''"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "681c71ed",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "Model summary (fused): 92 layers, 25,842,655 parameters, 0 gradients, 78.7 GFLOPs\n",
+      "\n",
+      "\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from '/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/weights/best_coco5class.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 9, 8400) (49.6 MB)\n",
+      "\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m starting export with onnx 1.19.1 opset 20...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m slimming with onnxslim 0.1.71...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m export success ✅ 1.3s, saved as '/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/weights/best_coco5class.onnx' (98.8 MB)\n",
+      "\n",
+      "Export complete (1.6s)\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/weights\u001b[0m\n",
+      "Predict:         yolo predict task=detect model=/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/weights/best_coco5class.onnx imgsz=640  \n",
+      "Validate:        yolo val task=detect model=/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/weights/best_coco5class.onnx imgsz=640 data=/home/cuuva/experiment/coco5class_exp/coco5class.yaml  \n",
+      "Visualize:       https://netron.app\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/weights/best_coco5class.onnx'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = YOLO(\"/home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class/weights/best_coco5class.pt\")\n",
+    "model.export(format=\"onnx\", imgsz=640, device=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "48b48641",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "1stagedetect",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

coco5class_exp/coco5class_v8m/5class/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/coco5class_exp/coco5class.yaml
+epochs: 300
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: coco5class_v8m
+name: 5class
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/coco5class_exp/coco5class_v8m/5class

coco5class_exp/coco5class_v8m/5class/results.csv

@@ -0,0 +1,91 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,1229.61,1.15644,1.1869,1.24197,0.47072,0.37359,0.38684,0.23748,1.32843,1.32885,1.37945,0.0670081,0.000333252,0.000333252
+2,2446.95,1.20417,1.2292,1.28156,0.61506,0.49446,0.54033,0.35796,1.1217,0.9894,1.21888,0.0340059,0.000664385,0.000664385
+3,3665.73,1.17197,1.16455,1.25771,0.64365,0.52586,0.57993,0.39502,1.07308,0.91944,1.18859,0.00100149,0.000993319,0.000993319
+4,4882.09,1.12694,1.08769,1.23057,0.67081,0.55916,0.61624,0.42356,1.02817,0.85259,1.16029,0.0009901,0.0009901,0.0009901
+5,6093.15,1.08789,1.02532,1.2045,0.67548,0.58031,0.64085,0.45344,0.99252,0.81462,1.13196,0.0009868,0.0009868,0.0009868
+6,7303.44,1.05683,0.97886,1.18507,0.70964,0.57547,0.65649,0.46687,0.97583,0.7861,1.122,0.0009835,0.0009835,0.0009835
+7,8514.17,1.03632,0.94608,1.17203,0.72479,0.58834,0.67208,0.48018,0.96537,0.77084,1.11509,0.0009802,0.0009802,0.0009802
+8,9723.56,1.02252,0.91965,1.16113,0.73526,0.58679,0.68078,0.48827,0.95671,0.76109,1.10845,0.0009769,0.0009769,0.0009769
+9,10933.1,1.00922,0.90315,1.15043,0.71924,0.6026,0.68299,0.49255,0.94869,0.75524,1.10165,0.0009736,0.0009736,0.0009736
+10,12143,0.99897,0.88175,1.14322,0.7326,0.60185,0.68718,0.49649,0.94452,0.75279,1.09849,0.0009703,0.0009703,0.0009703
+11,13352.4,0.98834,0.87084,1.13633,0.74018,0.60825,0.69146,0.5012,0.94039,0.7534,1.09568,0.000967,0.000967,0.000967
+12,14562.5,0.98102,0.85617,1.1302,0.75324,0.60639,0.69659,0.5054,0.93718,0.75394,1.09293,0.0009637,0.0009637,0.0009637
+13,15772.7,0.97347,0.84465,1.12479,0.74515,0.61443,0.69847,0.50866,0.93383,0.75656,1.09052,0.0009604,0.0009604,0.0009604
+14,16982.4,0.96684,0.83633,1.12128,0.76161,0.60171,0.70019,0.5114,0.93049,0.75748,1.08756,0.0009571,0.0009571,0.0009571
+15,18192,0.95844,0.82148,1.11621,0.77139,0.60114,0.70214,0.51338,0.92661,0.75567,1.0841,0.0009538,0.0009538,0.0009538
+16,19401.6,0.95559,0.81514,1.1125,0.77843,0.60163,0.70578,0.5173,0.92289,0.75131,1.08134,0.0009505,0.0009505,0.0009505
+17,20612.2,0.94744,0.80473,1.10934,0.77587,0.60808,0.70924,0.52165,0.91891,0.74384,1.07826,0.0009472,0.0009472,0.0009472
+18,21821.9,0.94327,0.79853,1.10471,0.77412,0.61318,0.71212,0.52466,0.91585,0.73733,1.07592,0.0009439,0.0009439,0.0009439
+19,23031.6,0.93986,0.79415,1.10244,0.76682,0.61869,0.71622,0.52834,0.91328,0.72983,1.07339,0.0009406,0.0009406,0.0009406
+20,24242.2,0.93772,0.78704,1.09781,0.75892,0.62992,0.71923,0.53047,0.91096,0.72349,1.07089,0.0009373,0.0009373,0.0009373
+21,25452.1,0.93122,0.78054,1.09898,0.76838,0.62483,0.72099,0.53249,0.90767,0.71747,1.06822,0.000934,0.000934,0.000934
+22,26662.5,0.92711,0.77642,1.09543,0.76712,0.62933,0.72526,0.53645,0.90473,0.71017,1.06649,0.0009307,0.0009307,0.0009307
+23,27873.1,0.92602,0.77119,1.09051,0.76479,0.63155,0.72686,0.53869,0.90338,0.70452,1.06445,0.0009274,0.0009274,0.0009274
+24,29083.5,0.92307,0.76622,1.09198,0.76451,0.63842,0.73169,0.54056,0.90219,0.69905,1.06316,0.0009241,0.0009241,0.0009241
+25,30293.8,0.92128,0.76072,1.08702,0.75967,0.64485,0.73278,0.54366,0.90059,0.69391,1.06133,0.0009208,0.0009208,0.0009208
+26,31504,0.91672,0.75566,1.08562,0.7597,0.64874,0.73347,0.54437,0.89909,0.68913,1.06016,0.0009175,0.0009175,0.0009175
+27,32714,0.91335,0.75118,1.08307,0.7692,0.64801,0.73511,0.54634,0.89851,0.68654,1.05949,0.0009142,0.0009142,0.0009142
+28,33924.7,0.91246,0.74878,1.0828,0.77617,0.64674,0.73688,0.54695,0.89814,0.68354,1.05914,0.0009109,0.0009109,0.0009109
+29,35134.9,0.90747,0.74389,1.0798,0.78163,0.64668,0.73865,0.54846,0.89658,0.68056,1.05799,0.0009076,0.0009076,0.0009076
+30,36345.6,0.90625,0.73901,1.07938,0.78008,0.656,0.74083,0.54798,0.89601,0.6777,1.05808,0.0009043,0.0009043,0.0009043
+31,37556.4,0.90127,0.73366,1.07423,0.78542,0.64873,0.7423,0.5498,0.89484,0.67485,1.05721,0.000901,0.000901,0.000901
+32,38767.3,0.90215,0.73312,1.07624,0.78021,0.65463,0.7436,0.5504,0.89391,0.6727,1.05659,0.0008977,0.0008977,0.0008977
+33,39977.8,0.90083,0.72933,1.0755,0.77123,0.65935,0.74486,0.55078,0.89279,0.6711,1.05578,0.0008944,0.0008944,0.0008944
+34,41188.5,0.89733,0.72643,1.07282,0.77507,0.65591,0.74712,0.55223,0.89173,0.66943,1.05465,0.0008911,0.0008911,0.0008911
+35,42399.2,0.89319,0.72212,1.07016,0.77746,0.65924,0.74888,0.55336,0.89082,0.66747,1.05417,0.0008878,0.0008878,0.0008878
+36,43609.6,0.89601,0.72119,1.06842,0.7779,0.66037,0.74843,0.55418,0.88987,0.66696,1.05229,0.0008845,0.0008845,0.0008845
+37,44819.8,0.89161,0.71751,1.06898,0.76647,0.66811,0.74785,0.5541,0.88967,0.66599,1.05225,0.0008812,0.0008812,0.0008812
+38,46030.1,0.88834,0.71369,1.06483,0.76199,0.66677,0.74688,0.55336,0.88975,0.66509,1.0519,0.0008779,0.0008779,0.0008779
+39,47240,0.88654,0.71002,1.06369,0.759,0.66741,0.7462,0.55443,0.8897,0.66559,1.05069,0.0008746,0.0008746,0.0008746
+40,48450.3,0.88769,0.70945,1.06666,0.77025,0.6617,0.74661,0.55391,0.88964,0.6652,1.05098,0.0008713,0.0008713,0.0008713
+41,49659.1,0.88283,0.70275,1.06431,0.77423,0.66271,0.74706,0.55394,0.88961,0.66512,1.05155,0.000868,0.000868,0.000868
+42,50869.4,0.88446,0.70161,1.06447,0.77198,0.66632,0.74751,0.55451,0.88969,0.66383,1.052,0.0008647,0.0008647,0.0008647
+43,52079.7,0.88044,0.69913,1.06198,0.76891,0.67012,0.74848,0.55617,0.88881,0.66277,1.05144,0.0008614,0.0008614,0.0008614
+44,53289.6,0.87873,0.69822,1.06145,0.76365,0.67158,0.74854,0.55606,0.88923,0.66143,1.05153,0.0008581,0.0008581,0.0008581
+45,54499.6,0.87671,0.69467,1.05878,0.76278,0.67406,0.74827,0.55471,0.88982,0.66134,1.05183,0.0008548,0.0008548,0.0008548
+46,55710,0.87585,0.69042,1.05866,0.7647,0.67788,0.75004,0.55588,0.88888,0.65963,1.05107,0.0008515,0.0008515,0.0008515
+47,56919.4,0.87419,0.68743,1.05706,0.76531,0.67797,0.75114,0.55712,0.8882,0.65944,1.04997,0.0008482,0.0008482,0.0008482
+48,58129.4,0.87516,0.68633,1.05811,0.75943,0.68193,0.75114,0.55735,0.88722,0.65912,1.04962,0.0008449,0.0008449,0.0008449
+49,59339,0.87393,0.68777,1.05446,0.76238,0.68228,0.75119,0.558,0.88583,0.65802,1.04863,0.0008416,0.0008416,0.0008416
+50,60549.4,0.86846,0.68081,1.05379,0.77182,0.67862,0.75375,0.55924,0.88599,0.6566,1.04869,0.0008383,0.0008383,0.0008383
+51,61759.9,0.86929,0.68082,1.05612,0.76525,0.68041,0.75292,0.55828,0.88586,0.65612,1.04938,0.000835,0.000835,0.000835
+52,62969.9,0.86741,0.67951,1.05621,0.76344,0.68311,0.75271,0.55792,0.88607,0.6561,1.04994,0.0008317,0.0008317,0.0008317
+53,64180.6,0.86651,0.6766,1.05158,0.75707,0.68068,0.75147,0.55707,0.88635,0.65645,1.0501,0.0008284,0.0008284,0.0008284
+54,65390.9,0.8654,0.67588,1.05465,0.76616,0.67917,0.75175,0.55738,0.88645,0.65667,1.0507,0.0008251,0.0008251,0.0008251
+55,66601.3,0.86238,0.67184,1.05168,0.75776,0.67996,0.75165,0.55664,0.88622,0.65807,1.05134,0.0008218,0.0008218,0.0008218
+56,67812.1,0.86422,0.67377,1.05452,0.75597,0.68119,0.75113,0.5572,0.88592,0.65844,1.05141,0.0008185,0.0008185,0.0008185
+57,69023.3,0.86095,0.66912,1.0496,0.76116,0.68014,0.75074,0.5581,0.88502,0.65844,1.05031,0.0008152,0.0008152,0.0008152
+58,70233.2,0.85865,0.66823,1.05075,0.77086,0.67439,0.75079,0.55848,0.88532,0.65904,1.05048,0.0008119,0.0008119,0.0008119
+59,71443.4,0.85689,0.6616,1.04504,0.76605,0.67181,0.75043,0.5578,0.88513,0.65965,1.05012,0.0008086,0.0008086,0.0008086
+60,72653.5,0.85795,0.66168,1.04595,0.76947,0.67209,0.75166,0.55741,0.8847,0.66034,1.04949,0.0008053,0.0008053,0.0008053
+61,73864.5,0.85672,0.66057,1.04478,0.7742,0.66643,0.75042,0.55645,0.88588,0.66176,1.04967,0.000802,0.000802,0.000802
+62,75074.9,0.85593,0.65982,1.04392,0.75821,0.68037,0.7503,0.55621,0.88474,0.66219,1.0488,0.0007987,0.0007987,0.0007987
+63,76285.4,0.85406,0.65689,1.04539,0.76942,0.66988,0.74948,0.55584,0.88397,0.66081,1.04806,0.0007954,0.0007954,0.0007954
+64,77495.9,0.85283,0.65283,1.04132,0.76562,0.67586,0.74927,0.55538,0.88428,0.6595,1.04828,0.0007921,0.0007921,0.0007921
+65,78706.3,0.85331,0.65549,1.04268,0.77189,0.66881,0.749,0.5559,0.88504,0.65795,1.04898,0.0007888,0.0007888,0.0007888
+66,79916.8,0.85181,0.6535,1.04268,0.78362,0.65943,0.748,0.55658,0.88508,0.65798,1.0487,0.0007855,0.0007855,0.0007855
+67,81126.9,0.85264,0.65308,1.04284,0.78844,0.65424,0.74864,0.55594,0.88607,0.6574,1.05003,0.0007822,0.0007822,0.0007822
+68,82337.8,0.84906,0.64895,1.03985,0.78274,0.65483,0.74873,0.55573,0.88611,0.65579,1.04997,0.0007789,0.0007789,0.0007789
+69,83547.9,0.84922,0.64789,1.03878,0.78557,0.65632,0.74839,0.55543,0.88631,0.65478,1.04974,0.0007756,0.0007756,0.0007756
+70,84758,0.84793,0.64511,1.03873,0.79071,0.65474,0.74944,0.5559,0.8871,0.65449,1.05048,0.0007723,0.0007723,0.0007723
+71,85968.3,0.84672,0.64492,1.04019,0.78804,0.65652,0.75034,0.55648,0.8873,0.65541,1.05106,0.000769,0.000769,0.000769
+72,87179.2,0.84476,0.64351,1.03792,0.77847,0.66854,0.75029,0.55665,0.88789,0.65627,1.05094,0.0007657,0.0007657,0.0007657
+73,88389.7,0.84464,0.64237,1.03724,0.77847,0.66462,0.75089,0.55685,0.88795,0.65656,1.05085,0.0007624,0.0007624,0.0007624
+74,89599.8,0.84379,0.63877,1.035,0.78097,0.6665,0.75104,0.55678,0.88865,0.65718,1.05112,0.0007591,0.0007591,0.0007591
+75,90810.1,0.84251,0.63592,1.03402,0.77879,0.67068,0.75178,0.55723,0.88943,0.65686,1.05237,0.0007558,0.0007558,0.0007558
+76,92020.3,0.8406,0.63693,1.0333,0.78477,0.66817,0.75119,0.55778,0.88911,0.65728,1.05182,0.0007525,0.0007525,0.0007525
+77,93230.3,0.84016,0.63763,1.03131,0.77849,0.67166,0.74961,0.55693,0.88874,0.65756,1.05089,0.0007492,0.0007492,0.0007492
+78,94440.8,0.83834,0.63282,1.03352,0.77658,0.66702,0.74947,0.55609,0.88939,0.65681,1.05193,0.0007459,0.0007459,0.0007459
+79,95650.4,0.83965,0.63259,1.03296,0.76483,0.67446,0.74878,0.55559,0.88897,0.65739,1.0515,0.0007426,0.0007426,0.0007426
+80,96861.1,0.83776,0.63197,1.03153,0.76791,0.67557,0.74974,0.55744,0.88942,0.65712,1.05189,0.0007393,0.0007393,0.0007393
+81,98071,0.83808,0.62934,1.03127,0.77543,0.66909,0.74876,0.55675,0.89092,0.65803,1.05278,0.000736,0.000736,0.000736
+82,99281.2,0.8356,0.62767,1.02933,0.76295,0.67705,0.74881,0.55611,0.89067,0.65785,1.05234,0.0007327,0.0007327,0.0007327
+83,100491,0.83636,0.62705,1.02787,0.76387,0.67536,0.74919,0.55588,0.89049,0.65771,1.0512,0.0007294,0.0007294,0.0007294
+84,101702,0.83436,0.62315,1.02817,0.77337,0.6695,0.74976,0.55728,0.89045,0.65776,1.05145,0.0007261,0.0007261,0.0007261
+85,102911,0.83495,0.62625,1.02993,0.76445,0.67239,0.74971,0.55698,0.88994,0.6582,1.05206,0.0007228,0.0007228,0.0007228
+86,104121,0.83187,0.62416,1.02909,0.76142,0.67786,0.75036,0.55586,0.8914,0.659,1.05314,0.0007195,0.0007195,0.0007195
+87,105330,0.83035,0.61933,1.02612,0.75112,0.68516,0.74852,0.55434,0.89238,0.65963,1.05316,0.0007162,0.0007162,0.0007162
+88,106540,0.83004,0.61958,1.02573,0.74852,0.68552,0.74878,0.55448,0.89167,0.66021,1.05276,0.0007129,0.0007129,0.0007129
+89,107750,0.82947,0.6179,1.02461,0.76123,0.67949,0.74907,0.55446,0.892,0.65969,1.05324,0.0007096,0.0007096,0.0007096
+90,108959,0.83,0.61727,1.02388,0.75264,0.67981,0.74969,0.55546,0.89226,0.65823,1.05408,0.0007063,0.0007063,0.0007063

coco5class_exp/train_coco5class.py

@@ -0,0 +1,16 @@
+from ultralytics import YOLO
+
+model = YOLO('yolov8m.pt')
+
+model.train(
+    data="/home/cuuva/experiment/coco5class_exp/coco5class.yaml",
+    epochs=300,
+    imgsz=640,
+    batch=-1,
+    device="cuda",
+    optimizer='AdamW',
+    lr0=0.001,
+    patience=40,
+    project='coco5class_v8m',
+    name='5class'
+)

custom_LP_detect/custom_LP.yaml

@@ -0,0 +1,33 @@
+# # path: datasets/VisDrone  # 데이터 경로
+# train: /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/image/license_plate/
+# val: /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/image/license_plate/
+# # test: images/test
+
+
+# # path: /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/
+
+# # train:
+# #   - image/license_plate/        # 이미지 폴더
+# # val:
+# #   - ../Validation/image/license_plate/
+
+# # 각 이미지에 대응하는 라벨 경로를 직접 지정
+# labels:
+#   train: /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/labels/license_plate/
+#   val: /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/labels/license_plate/
+
+# nc: 1
+# names: ['lp']
+
+# custom_LP.yaml
+
+# 데이터셋 경로
+train: /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/
+val: /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/images/license_plate/
+
+# 클래스 수
+nc: 1
+
+# 클래스 이름
+names: ['lp']
+

custom_LP_detect/easyocr.py

@@ -0,0 +1,38 @@
+import easyocr
+import cv2
+from matplotlib import pyplot as plt
+import time  # ⬅ 추가
+
+# 1. EasyOCR Reader 생성
+reader = easyocr.Reader(['ko', 'en'], gpu=False)
+
+# 2. 이미지 불러오기
+# image_path = '/home/cuuva/다운로드/test/ocr_resized.png'
+image_path = '/home/cuuva/experiment/custom_LP_detect/ocr2.png'
+image = cv2.imread(image_path)
+image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+# ------------------------
+# 3. OCR 수행 및 시간 측정
+# ------------------------
+start_time = time.time()
+results = reader.readtext(image_rgb, detail=1)
+end_time = time.time()
+print(f"Inference time: {end_time - start_time:.3f} seconds")
+
+# 4. 결과 출력 및 시각화
+for (bbox, text, prob) in results:
+    print(f"Detected text: {text}, Confidence: {prob:.2f}")
+    
+    # 바운딩 박스
+    top_left = tuple(map(int, bbox[0]))
+    bottom_right = tuple(map(int, bbox[2]))
+    cv2.rectangle(image_rgb, top_left, bottom_right, (0, 255, 0), 2)
+    cv2.putText(image_rgb, text, (top_left[0], top_left[1]-10), 
+                cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 2)
+
+# 5. 시각화
+plt.figure(figsize=(10,6))
+plt.imshow(image_rgb)
+plt.axis('off')
+plt.show()

custom_LP_detect/lp_detect/epo_100_frac_0_1/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/custom_LP_detect/custom_LP.yaml
+epochs: 100
+time: null
+patience: 30
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: lp_detect
+name: epo_100_frac_0_1
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 0.1
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/custom_LP_detect/lp_detect/epo_100_frac_0_1

custom_LP_detect/lp_detect/epo_100_frac_0_1/results.csv

@@ -0,0 +1,49 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,425.165,2.19122,3.26902,0.82512,0.6796,0.40305,0.46173,0.21578,1.89595,1.23584,0.8364,0.0670556,0.000332772,0.000332772
+2,808.781,1.64521,0.75428,0.75617,0.65304,0.41129,0.47132,0.22205,1.90004,1.21189,0.83069,0.034049,0.000659511,0.000659511
+3,1231.51,1.52713,0.69414,0.75118,0.66802,0.45492,0.5031,0.24661,1.7403,1.08313,0.81498,0.00103577,0.00097965,0.00097965
+4,1691.33,1.43927,0.65043,0.74699,0.65894,0.45254,0.51006,0.25925,1.74713,1.13768,0.81,0.0009703,0.0009703,0.0009703
+5,2257.87,1.36285,0.61528,0.74381,0.64243,0.41284,0.47289,0.20355,1.98662,1.21622,0.82419,0.0009604,0.0009604,0.0009604
+6,2784.98,1.32167,0.59366,0.7425,0.62479,0.45232,0.49886,0.25337,1.72637,1.15112,0.81075,0.0009505,0.0009505,0.0009505
+7,3392.08,1.29427,0.57982,0.74102,0.61384,0.47403,0.50783,0.26403,1.6687,1.12246,0.80667,0.0009406,0.0009406,0.0009406
+8,4001.3,1.26971,0.57071,0.74022,0.64064,0.45808,0.51302,0.2696,1.63154,1.13117,0.80421,0.0009307,0.0009307,0.0009307
+9,4654.23,1.24975,0.56167,0.74002,0.64587,0.47878,0.53826,0.28473,1.6386,1.03233,0.80128,0.0009208,0.0009208,0.0009208
+10,5294.75,1.22996,0.55374,0.73855,0.63738,0.48036,0.52939,0.27517,1.65346,1.05963,0.80323,0.0009109,0.0009109,0.0009109
+11,5890.25,1.21637,0.5461,0.73821,0.62227,0.48528,0.53838,0.2876,1.5961,1.05144,0.79948,0.000901,0.000901,0.000901
+12,6506.41,1.20813,0.54059,0.73824,0.62561,0.48721,0.53111,0.28706,1.57482,1.05719,0.79905,0.0008911,0.0008911,0.0008911
+13,7072.89,1.19407,0.53627,0.73775,0.65056,0.48666,0.54766,0.28064,1.65217,1.00232,0.80387,0.0008812,0.0008812,0.0008812
+14,7702.37,1.18192,0.52905,0.73707,0.63316,0.48291,0.53362,0.28604,1.58725,1.05205,0.79932,0.0008713,0.0008713,0.0008713
+15,8322.77,1.17533,0.52539,0.7365,0.63463,0.48576,0.53978,0.28057,1.62984,1.04773,0.80217,0.0008614,0.0008614,0.0008614
+16,8945.4,1.16706,0.52089,0.73663,0.63386,0.47596,0.53067,0.27845,1.6132,1.05199,0.80074,0.0008515,0.0008515,0.0008515
+17,9549.4,1.16206,0.51874,0.7363,0.63145,0.48427,0.54143,0.29506,1.57316,1.02901,0.79965,0.0008416,0.0008416,0.0008416
+18,10183,1.15319,0.51494,0.73602,0.63691,0.48989,0.54739,0.29699,1.54797,0.98616,0.79701,0.0008317,0.0008317,0.0008317
+19,10864.6,1.14836,0.51207,0.73527,0.63076,0.48931,0.54466,0.28707,1.59721,1.01195,0.79987,0.0008218,0.0008218,0.0008218
+20,11543.9,1.13952,0.50831,0.73561,0.63679,0.48773,0.54475,0.2852,1.60959,1.00444,0.8005,0.0008119,0.0008119,0.0008119
+21,12149.9,1.13458,0.50721,0.73546,0.6347,0.49139,0.54533,0.28571,1.59979,1.00025,0.80068,0.000802,0.000802,0.000802
+22,12807.7,1.13033,0.50404,0.73513,0.64262,0.48644,0.54558,0.28325,1.61616,1.00355,0.80181,0.0007921,0.0007921,0.0007921
+23,13457.6,1.12219,0.50083,0.73509,0.63476,0.49074,0.54641,0.28606,1.60342,1.00548,0.80097,0.0007822,0.0007822,0.0007822
+24,14045.2,1.12299,0.50079,0.73451,0.63356,0.48964,0.54538,0.2886,1.58839,1.00563,0.80022,0.0007723,0.0007723,0.0007723
+25,14682.9,1.11743,0.49773,0.7344,0.63638,0.48854,0.54547,0.28935,1.58982,1.00766,0.80023,0.0007624,0.0007624,0.0007624
+26,15313,1.11159,0.49428,0.73421,0.63273,0.49187,0.54717,0.29134,1.5834,1.00419,0.79976,0.0007525,0.0007525,0.0007525
+27,15949.4,1.1079,0.49312,0.73477,0.62927,0.49237,0.54658,0.29279,1.57963,1.00732,0.79923,0.0007426,0.0007426,0.0007426
+28,16590.8,1.10157,0.49046,0.73422,0.63069,0.49079,0.54587,0.29366,1.57586,1.01084,0.79888,0.0007327,0.0007327,0.0007327
+29,17238.4,1.10082,0.48931,0.73398,0.62821,0.49129,0.54513,0.29312,1.58014,1.01325,0.79913,0.0007228,0.0007228,0.0007228
+30,17863.7,1.09788,0.4879,0.73401,0.62898,0.49109,0.54562,0.29262,1.58446,1.01239,0.79944,0.0007129,0.0007129,0.0007129
+31,18540.5,1.09284,0.48642,0.73404,0.62873,0.49098,0.54562,0.29185,1.58875,1.01304,0.79989,0.000703,0.000703,0.000703
+32,19186.3,1.09083,0.48494,0.73416,0.62829,0.49115,0.54536,0.29198,1.5888,1.0143,0.80005,0.0006931,0.0006931,0.0006931
+33,19839.8,1.08699,0.48398,0.73355,0.62734,0.49145,0.54532,0.29191,1.58867,1.0148,0.80002,0.0006832,0.0006832,0.0006832
+34,20504,1.08597,0.48141,0.73393,0.62698,0.4914,0.54523,0.29118,1.59253,1.01673,0.80031,0.0006733,0.0006733,0.0006733
+35,21174.5,1.08151,0.48094,0.7331,0.62684,0.49147,0.54545,0.29099,1.59534,1.01703,0.80055,0.0006634,0.0006634,0.0006634
+36,21848.8,1.08102,0.47931,0.73376,0.62743,0.49117,0.54571,0.291,1.59622,1.01618,0.80068,0.0006535,0.0006535,0.0006535
+37,22473.2,1.07841,0.47814,0.73345,0.62733,0.49067,0.54546,0.29072,1.59795,1.0186,0.80085,0.0006436,0.0006436,0.0006436
+38,23119.6,1.07543,0.47798,0.73324,0.62685,0.49,0.54491,0.29029,1.59986,1.0207,0.80101,0.0006337,0.0006337,0.0006337
+39,23782.1,1.073,0.47657,0.7333,0.6263,0.49022,0.54493,0.29014,1.6003,1.02031,0.80113,0.0006238,0.0006238,0.0006238
+40,24405.1,1.07203,0.47559,0.73325,0.62578,0.49105,0.54528,0.2901,1.60029,1.01927,0.80117,0.0006139,0.0006139,0.0006139
+41,25029.6,1.06935,0.47511,0.73316,0.62636,0.49111,0.54574,0.29017,1.60051,1.01941,0.80117,0.000604,0.000604,0.000604
+42,25669.9,1.06678,0.47396,0.7325,0.62768,0.49078,0.54632,0.29068,1.59918,1.01861,0.80112,0.0005941,0.0005941,0.0005941
+43,26327.5,1.06205,0.46927,0.73269,0.628,0.49054,0.5466,0.29107,1.59911,1.02009,0.80121,0.0005842,0.0005842,0.0005842
+44,27008.8,1.05982,0.47072,0.7323,0.6289,0.49022,0.54753,0.29179,1.59858,1.01947,0.80132,0.0005743,0.0005743,0.0005743
+45,27654.8,1.05797,0.46855,0.73287,0.62908,0.48979,0.5479,0.29226,1.59741,1.01905,0.80134,0.0005644,0.0005644,0.0005644
+46,28273.5,1.05607,0.46781,0.73253,0.63035,0.4887,0.54799,0.29264,1.5944,1.01842,0.80121,0.0005545,0.0005545,0.0005545
+47,28888.8,1.05285,0.46653,0.7322,0.6308,0.48859,0.54824,0.293,1.59415,1.01825,0.8012,0.0005446,0.0005446,0.0005446
+48,29666.5,1.05326,0.46586,0.73276,0.63148,0.48755,0.54793,0.29316,1.59252,1.01869,0.80116,0.0005347,0.0005347,0.0005347

custom_LP_detect/lp_detect/epo_200_frac_0_2/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/custom_LP_detect/custom_LP.yaml
+epochs: 200
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: lp_detect
+name: epo_200_frac_0_2
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 0.2
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_2

custom_LP_detect/lp_detect/epo_200_frac_0_2/results.csv

@@ -0,0 +1,120 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,723.844,2.07408,2.21817,0.8098,0.71536,0.48978,0.53151,0.25262,1.73505,0.9444,0.81842,0.0670278,0.000333053,0.000333053
+2,1435.55,1.58293,0.74137,0.75875,0.79959,0.52345,0.59289,0.31563,1.52597,0.81303,0.79943,0.0340245,0.000663087,0.000663087
+3,2176.86,1.46606,0.67807,0.75444,0.7983,0.51441,0.60086,0.31887,1.55418,0.84581,0.80237,0.00101788,0.000989822,0.000989822
+4,2966.54,1.38407,0.63657,0.75046,0.80813,0.53779,0.62884,0.33972,1.4425,0.71651,0.79698,0.00098515,0.00098515,0.00098515
+5,3858.8,1.31864,0.60203,0.74793,0.82935,0.55475,0.64409,0.35485,1.41393,0.69283,0.79108,0.0009802,0.0009802,0.0009802
+6,4726.74,1.27895,0.58078,0.74608,0.85718,0.561,0.67905,0.39662,1.32381,0.66201,0.78561,0.00097525,0.00097525,0.00097525
+7,5601.21,1.25517,0.56979,0.74525,0.83164,0.57179,0.6738,0.38316,1.35157,0.64819,0.78647,0.0009703,0.0009703,0.0009703
+8,6485.42,1.23291,0.55671,0.74456,0.84298,0.56348,0.66817,0.38618,1.31,0.64487,0.78634,0.00096535,0.00096535,0.00096535
+9,7453.91,1.21657,0.54911,0.74341,0.84957,0.57325,0.68451,0.39491,1.31351,0.63027,0.7854,0.0009604,0.0009604,0.0009604
+10,8361.51,1.20022,0.54134,0.74261,0.84781,0.57741,0.68773,0.40126,1.29022,0.61634,0.78321,0.00095545,0.00095545,0.00095545
+11,9240.95,1.18858,0.53458,0.74274,0.83864,0.57749,0.68667,0.40412,1.27972,0.61789,0.78315,0.0009505,0.0009505,0.0009505
+12,10161.6,1.1797,0.52989,0.74227,0.8378,0.57844,0.68827,0.39961,1.30056,0.61911,0.78465,0.00094555,0.00094555,0.00094555
+13,11092.6,1.16883,0.52609,0.74147,0.83417,0.57881,0.68672,0.40123,1.29338,0.61691,0.78423,0.0009406,0.0009406,0.0009406
+14,12068,1.16096,0.52096,0.74113,0.83328,0.58014,0.68871,0.40368,1.28619,0.61376,0.7837,0.00093565,0.00093565,0.00093565
+15,13026.6,1.15413,0.51717,0.74075,0.83333,0.58048,0.68958,0.40327,1.29169,0.61364,0.78402,0.0009307,0.0009307,0.0009307
+16,13913.5,1.14571,0.51344,0.74134,0.83365,0.58055,0.69056,0.40359,1.29405,0.61359,0.78406,0.00092575,0.00092575,0.00092575
+17,14779.3,1.14068,0.51065,0.74023,0.83525,0.5819,0.69303,0.4057,1.29086,0.61156,0.78377,0.0009208,0.0009208,0.0009208
+18,15716.1,1.13238,0.50791,0.74038,0.83657,0.58256,0.69503,0.4071,1.28866,0.60962,0.78357,0.00091585,0.00091585,0.00091585
+19,16629.1,1.12878,0.5051,0.74076,0.83729,0.58302,0.69698,0.40788,1.29062,0.60915,0.78367,0.0009109,0.0009109,0.0009109
+20,17521.1,1.12488,0.50285,0.7399,0.83782,0.58433,0.69918,0.41006,1.28735,0.60737,0.78341,0.00090595,0.00090595,0.00090595
+21,18492.9,1.11971,0.50015,0.74021,0.83857,0.5858,0.70192,0.41283,1.2834,0.60603,0.7831,0.000901,0.000901,0.000901
+22,19399.6,1.11692,0.49908,0.73945,0.83934,0.58661,0.70345,0.41335,1.28588,0.6061,0.78323,0.00089605,0.00089605,0.00089605
+23,20294.5,1.11215,0.49759,0.73928,0.83927,0.58738,0.70438,0.41399,1.28643,0.60604,0.78324,0.0008911,0.0008911,0.0008911
+24,21151.7,1.10788,0.49421,0.73984,0.84037,0.58837,0.7059,0.41548,1.28522,0.60566,0.78319,0.00088615,0.00088615,0.00088615
+25,22088.9,1.10476,0.49299,0.73944,0.84095,0.58922,0.70722,0.41772,1.28132,0.60488,0.78295,0.0008812,0.0008812,0.0008812
+26,23013.5,1.10147,0.4912,0.73954,0.84264,0.58976,0.7089,0.41965,1.27934,0.60437,0.78281,0.00087625,0.00087625,0.00087625
+27,23959.5,1.09802,0.48966,0.73893,0.84349,0.59073,0.71016,0.42063,1.27834,0.60363,0.78281,0.0008713,0.0008713,0.0008713
+28,24847.5,1.0993,0.49022,0.7391,0.84557,0.59096,0.71174,0.42268,1.27449,0.60229,0.78259,0.00086635,0.00086635,0.00086635
+29,25860.6,1.093,0.48708,0.73963,0.84576,0.59192,0.71262,0.4233,1.27515,0.60178,0.7827,0.0008614,0.0008614,0.0008614
+30,26820.9,1.09207,0.48677,0.73836,0.84635,0.59256,0.71374,0.42469,1.27218,0.6003,0.78259,0.00085645,0.00085645,0.00085645
+31,27827.5,1.08848,0.4848,0.73905,0.84662,0.59335,0.71493,0.42536,1.27182,0.5997,0.78257,0.0008515,0.0008515,0.0008515
+32,28795.5,1.08572,0.48334,0.73856,0.84686,0.59368,0.71559,0.42569,1.27282,0.59917,0.78265,0.00084655,0.00084655,0.00084655
+33,29724.5,1.08286,0.48141,0.73857,0.848,0.59357,0.71659,0.427,1.27097,0.59897,0.7826,0.0008416,0.0008416,0.0008416
+34,30631.6,1.07959,0.47956,0.73879,0.84889,0.59343,0.71705,0.4274,1.27074,0.59846,0.78264,0.00083665,0.00083665,0.00083665
+35,31589,1.07928,0.47946,0.73861,0.85032,0.59362,0.71804,0.42825,1.26937,0.59744,0.78259,0.0008317,0.0008317,0.0008317
+36,32533.2,1.0764,0.47765,0.73841,0.85041,0.5939,0.71861,0.4288,1.26698,0.59606,0.78256,0.00082675,0.00082675,0.00082675
+37,33532.7,1.07279,0.47748,0.73848,0.85122,0.59396,0.71889,0.4286,1.26801,0.59593,0.78261,0.0008218,0.0008218,0.0008218
+38,34501.6,1.07425,0.47674,0.73852,0.85176,0.59404,0.71884,0.42911,1.26599,0.59374,0.78256,0.00081685,0.00081685,0.00081685
+39,35373.3,1.06917,0.47443,0.73859,0.85126,0.5943,0.71847,0.42856,1.2662,0.59232,0.78254,0.0008119,0.0008119,0.0008119
+40,36284.4,1.06731,0.47499,0.73819,0.85083,0.59518,0.71814,0.42813,1.26535,0.59079,0.78245,0.00080695,0.00080695,0.00080695
+41,37255.6,1.06678,0.4734,0.73795,0.85094,0.59498,0.71785,0.42774,1.26787,0.59061,0.78271,0.000802,0.000802,0.000802
+42,38243.5,1.06518,0.47232,0.73774,0.85095,0.59521,0.71781,0.42733,1.26949,0.59047,0.78285,0.00079705,0.00079705,0.00079705
+43,39261,1.06286,0.4716,0.73768,0.85042,0.59552,0.71796,0.42699,1.27037,0.59054,0.78297,0.0007921,0.0007921,0.0007921
+44,40291.3,1.06134,0.47054,0.73818,0.85007,0.59581,0.71792,0.42701,1.26932,0.58986,0.78306,0.00078715,0.00078715,0.00078715
+45,41169.5,1.06046,0.47018,0.73767,0.84986,0.59616,0.71769,0.42698,1.26869,0.58898,0.78312,0.0007822,0.0007822,0.0007822
+46,42069.8,1.05857,0.46901,0.73773,0.84951,0.59609,0.71731,0.42719,1.2667,0.58819,0.7831,0.00077725,0.00077725,0.00077725
+47,43013,1.05927,0.46992,0.73736,0.84897,0.59562,0.7171,0.42771,1.26447,0.58815,0.7831,0.0007723,0.0007723,0.0007723
+48,43920.9,1.05574,0.46823,0.73798,0.84852,0.59561,0.71718,0.42801,1.26351,0.58791,0.78306,0.00076735,0.00076735,0.00076735
+49,44775.4,1.05387,0.46688,0.738,0.84847,0.59554,0.71709,0.42861,1.26226,0.58731,0.78301,0.0007624,0.0007624,0.0007624
+50,45689.3,1.05387,0.4664,0.73749,0.8488,0.59536,0.71721,0.42878,1.26178,0.58744,0.78312,0.00075745,0.00075745,0.00075745
+51,46596.5,1.05139,0.46497,0.73758,0.84891,0.59489,0.71677,0.42893,1.26034,0.58708,0.7831,0.0007525,0.0007525,0.0007525
+52,47508.9,1.05,0.46428,0.73772,0.84781,0.59533,0.71665,0.42971,1.25555,0.58558,0.78288,0.00074755,0.00074755,0.00074755
+53,48398.7,1.04705,0.46364,0.73732,0.84742,0.5955,0.71633,0.43027,1.25425,0.58563,0.78287,0.0007426,0.0007426,0.0007426
+54,49319,1.04838,0.46313,0.73768,0.84778,0.59557,0.71638,0.4307,1.25382,0.58552,0.78285,0.00073765,0.00073765,0.00073765
+55,50247,1.04533,0.46342,0.73716,0.84712,0.59542,0.71595,0.43027,1.25482,0.58628,0.78296,0.0007327,0.0007327,0.0007327
+56,51158.6,1.04601,0.46289,0.73734,0.84656,0.59535,0.71571,0.43038,1.25218,0.58575,0.78287,0.00072775,0.00072775,0.00072775
+57,52060.4,1.04521,0.46146,0.73717,0.84609,0.59557,0.71554,0.42979,1.25365,0.58606,0.78291,0.0007228,0.0007228,0.0007228
+58,52948.6,1.04108,0.4611,0.73755,0.84617,0.59564,0.71516,0.42974,1.2528,0.58554,0.78277,0.00071785,0.00071785,0.00071785
+59,53851.7,1.04144,0.46092,0.73741,0.84688,0.59533,0.7151,0.42948,1.25352,0.58561,0.78288,0.0007129,0.0007129,0.0007129
+60,54761.6,1.04046,0.46076,0.73733,0.84669,0.59566,0.71514,0.42974,1.252,0.58475,0.78275,0.00070795,0.00070795,0.00070795
+61,55685.7,1.04032,0.45854,0.73725,0.84569,0.59584,0.71467,0.42958,1.2517,0.58468,0.7828,0.000703,0.000703,0.000703
+62,56569.8,1.03915,0.45977,0.73723,0.84506,0.5953,0.7138,0.42879,1.25329,0.58518,0.78292,0.00069805,0.00069805,0.00069805
+63,57414,1.03748,0.45974,0.73704,0.8443,0.59572,0.71358,0.42875,1.25115,0.58496,0.78288,0.0006931,0.0006931,0.0006931
+64,58314.8,1.03718,0.45829,0.73712,0.8441,0.59597,0.71321,0.42898,1.24963,0.58386,0.78284,0.00068815,0.00068815,0.00068815
+65,59309.3,1.0336,0.45655,0.73752,0.84417,0.59533,0.71259,0.42889,1.249,0.58449,0.78287,0.0006832,0.0006832,0.0006832
+66,60355.6,1.03305,0.45657,0.73699,0.84394,0.59586,0.71247,0.42789,1.25232,0.58524,0.78327,0.00067825,0.00067825,0.00067825
+67,61448.1,1.03239,0.45607,0.73649,0.84423,0.59496,0.7122,0.42678,1.25673,0.58648,0.7836,0.0006733,0.0006733,0.0006733
+68,62266.1,1.0323,0.4561,0.73743,0.84402,0.59492,0.71213,0.42718,1.25533,0.5863,0.78358,0.00066835,0.00066835,0.00066835
+69,63152.2,1.03196,0.45606,0.73684,0.84396,0.59532,0.71293,0.42809,1.25406,0.58613,0.78358,0.0006634,0.0006634,0.0006634
+70,64016.7,1.02885,0.45484,0.73678,0.84357,0.59555,0.71263,0.42779,1.25569,0.58589,0.78384,0.00065845,0.00065845,0.00065845
+71,64826.5,1.02932,0.45468,0.73624,0.8434,0.59543,0.71237,0.42749,1.25596,0.58556,0.78385,0.0006535,0.0006535,0.0006535
+72,65752.7,1.02745,0.45392,0.73635,0.84342,0.59537,0.71274,0.42694,1.25778,0.58593,0.78397,0.00064855,0.00064855,0.00064855
+73,66585.7,1.02823,0.45346,0.73643,0.84388,0.59528,0.71267,0.42716,1.25664,0.58552,0.78397,0.0006436,0.0006436,0.0006436
+74,67526.8,1.02704,0.45321,0.73652,0.8441,0.59536,0.71279,0.42721,1.25571,0.58557,0.78388,0.00063865,0.00063865,0.00063865
+75,68439.5,1.02634,0.45238,0.73673,0.84368,0.59539,0.71238,0.42706,1.25717,0.58527,0.78401,0.0006337,0.0006337,0.0006337
+76,69308.4,1.02555,0.45177,0.73677,0.84342,0.59574,0.7123,0.42759,1.25365,0.58387,0.78379,0.00062875,0.00062875,0.00062875
+77,70213.2,1.02411,0.45217,0.7366,0.84341,0.59567,0.71208,0.42819,1.25214,0.58318,0.78374,0.0006238,0.0006238,0.0006238
+78,71106.2,1.02452,0.45112,0.73668,0.84323,0.59597,0.7122,0.42839,1.25092,0.58284,0.78377,0.00061885,0.00061885,0.00061885
+79,71948.2,1.02228,0.4517,0.73634,0.8434,0.59549,0.71218,0.42883,1.25063,0.58309,0.7838,0.0006139,0.0006139,0.0006139
+80,72809,1.02226,0.45105,0.73632,0.84323,0.59608,0.71237,0.42921,1.25093,0.58295,0.78379,0.00060895,0.00060895,0.00060895
+81,73699.7,1.01907,0.45043,0.73658,0.84288,0.59658,0.71228,0.42898,1.25188,0.58351,0.78389,0.000604,0.000604,0.000604
+82,74534,1.01756,0.44863,0.7365,0.84282,0.59687,0.7123,0.42911,1.25165,0.58293,0.78376,0.00059905,0.00059905,0.00059905
+83,75299.9,1.01809,0.44852,0.7365,0.84414,0.59672,0.71228,0.42976,1.24945,0.58193,0.7836,0.0005941,0.0005941,0.0005941
+84,76174.7,1.01855,0.44886,0.73674,0.84476,0.59668,0.71223,0.43007,1.24982,0.58136,0.78368,0.00058915,0.00058915,0.00058915
+85,77116.1,1.01508,0.44744,0.7366,0.8459,0.59618,0.71246,0.43051,1.25009,0.58153,0.78368,0.0005842,0.0005842,0.0005842
+86,77958.9,1.01681,0.44807,0.73641,0.84586,0.59595,0.7126,0.43031,1.25119,0.58184,0.78369,0.00057925,0.00057925,0.00057925
+87,78808.3,1.01515,0.4474,0.73596,0.84702,0.59584,0.71283,0.43081,1.25023,0.5818,0.7836,0.0005743,0.0005743,0.0005743
+88,79585.1,1.01586,0.44747,0.73669,0.8478,0.59595,0.71281,0.43096,1.24937,0.58146,0.78363,0.00056935,0.00056935,0.00056935
+89,80465.8,1.0139,0.44605,0.73666,0.84835,0.59569,0.71249,0.4305,1.24943,0.58092,0.78359,0.0005644,0.0005644,0.0005644
+90,81323.6,1.0129,0.44773,0.73644,0.84768,0.59594,0.71238,0.43068,1.24929,0.58044,0.78349,0.00055945,0.00055945,0.00055945
+91,82215.9,1.01239,0.44594,0.73642,0.84843,0.59547,0.71236,0.43089,1.24829,0.57989,0.78341,0.0005545,0.0005545,0.0005545
+92,83222.6,1.01113,0.44485,0.73649,0.84812,0.59581,0.71223,0.43108,1.24659,0.57961,0.78332,0.00054955,0.00054955,0.00054955
+93,84148.1,1.0117,0.4459,0.73583,0.8483,0.59602,0.7128,0.43193,1.24833,0.57978,0.78338,0.0005446,0.0005446,0.0005446
+94,84982.5,1.01133,0.44578,0.73597,0.84877,0.59574,0.71288,0.4319,1.24898,0.57997,0.78336,0.00053965,0.00053965,0.00053965
+95,85837.6,1.0102,0.44423,0.73598,0.84997,0.59581,0.71347,0.43281,1.24806,0.57973,0.78346,0.0005347,0.0005347,0.0005347
+96,86712.6,1.00786,0.44329,0.73634,0.85032,0.59589,0.71382,0.43264,1.24666,0.579,0.78353,0.00052975,0.00052975,0.00052975
+97,87527.7,1.00819,0.44409,0.7361,0.85034,0.59657,0.71429,0.4337,1.24796,0.5787,0.78375,0.0005248,0.0005248,0.0005248
+98,88410.7,1.00721,0.44364,0.73598,0.85114,0.59654,0.71453,0.43436,1.24578,0.57753,0.78367,0.00051985,0.00051985,0.00051985
+99,89268.2,1.00668,0.44232,0.73614,0.8514,0.59622,0.71457,0.43365,1.24572,0.57727,0.78366,0.0005149,0.0005149,0.0005149
+100,90166.9,1.006,0.44285,0.73568,0.85077,0.59689,0.71504,0.43387,1.24547,0.57699,0.7837,0.00050995,0.00050995,0.00050995
+101,91030.7,1.00632,0.44333,0.73614,0.85074,0.59667,0.71478,0.43345,1.24594,0.57658,0.78379,0.000505,0.000505,0.000505
+102,91898.6,1.0049,0.4419,0.73609,0.85025,0.59671,0.71469,0.43323,1.24495,0.57607,0.7839,0.00050005,0.00050005,0.00050005
+103,92757.1,1.00389,0.44232,0.73601,0.85002,0.5976,0.71476,0.43376,1.24281,0.57503,0.78374,0.0004951,0.0004951,0.0004951
+104,93647.1,1.00465,0.44161,0.73614,0.85042,0.59716,0.71433,0.43331,1.24269,0.57479,0.78374,0.00049015,0.00049015,0.00049015
+105,94524.6,1.00305,0.44075,0.7366,0.85021,0.59754,0.71437,0.43329,1.24264,0.57482,0.78376,0.0004852,0.0004852,0.0004852
+106,95413,1.00292,0.44186,0.73555,0.8507,0.59749,0.71458,0.43353,1.24281,0.57477,0.78373,0.00048025,0.00048025,0.00048025
+107,96326,1.00177,0.44003,0.73648,0.85025,0.59773,0.71431,0.43323,1.24327,0.57494,0.78371,0.0004753,0.0004753,0.0004753
+108,97200.5,1.00182,0.43963,0.73618,0.85076,0.59763,0.7141,0.43336,1.24347,0.57502,0.78377,0.00047035,0.00047035,0.00047035
+109,98112.8,1.00165,0.44068,0.73598,0.85159,0.59773,0.71455,0.43388,1.24267,0.57484,0.78378,0.0004654,0.0004654,0.0004654
+110,98990.2,1.00146,0.44026,0.73564,0.85225,0.59762,0.71468,0.4351,1.24285,0.57539,0.78399,0.00046045,0.00046045,0.00046045
+111,99878.2,0.99901,0.43873,0.73619,0.85258,0.59716,0.71487,0.43525,1.24322,0.57538,0.78399,0.0004555,0.0004555,0.0004555
+112,100751,1.00021,0.43983,0.73559,0.85277,0.59677,0.71473,0.43536,1.24265,0.57574,0.78401,0.00045055,0.00045055,0.00045055
+113,101666,0.99945,0.44007,0.73567,0.85204,0.59666,0.71494,0.43523,1.24406,0.57614,0.78416,0.0004456,0.0004456,0.0004456
+114,102576,0.99743,0.43739,0.73573,0.85159,0.59683,0.71524,0.43559,1.24502,0.57655,0.78437,0.00044065,0.00044065,0.00044065
+115,103491,0.99598,0.43738,0.73575,0.85145,0.59645,0.71509,0.43535,1.24706,0.57778,0.78454,0.0004357,0.0004357,0.0004357
+116,104350,0.99795,0.43911,0.73581,0.85105,0.59644,0.71533,0.43573,1.2467,0.57804,0.78447,0.00043075,0.00043075,0.00043075
+117,105219,0.99677,0.43726,0.73531,0.85049,0.59603,0.71472,0.43488,1.24952,0.57886,0.78466,0.0004258,0.0004258,0.0004258
+118,106054,0.9939,0.43704,0.73616,0.85085,0.59601,0.71475,0.43429,1.24998,0.57921,0.78475,0.00042085,0.00042085,0.00042085
+119,106906,0.99571,0.43731,0.73575,0.8514,0.59575,0.71476,0.43421,1.25146,0.57974,0.7849,0.0004159,0.0004159,0.0004159

custom_LP_detect/lp_detect/epo_200_frac_0_22/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/custom_LP_detect/custom_LP.yaml
+epochs: 200
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: lp_detect
+name: epo_200_frac_0_22
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 0.2
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22

custom_LP_detect/lp_detect/epo_200_frac_0_22/results.csv

@@ -0,0 +1,89 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,670.082,2.08443,2.44821,0.81081,0.71851,0.47457,0.52971,0.23364,1.83755,0.95405,0.8215,0.0670278,0.000333053,0.000333053
+2,1313.75,1.58716,0.74414,0.75968,0.81677,0.52719,0.61301,0.3289,1.5445,0.85338,0.8027,0.0340245,0.000663087,0.000663087
+3,2135,1.47432,0.68417,0.75414,0.80856,0.53261,0.6084,0.32633,1.42827,0.7321,0.79235,0.00101788,0.000989822,0.000989822
+4,2940.55,1.38928,0.63927,0.75077,0.83619,0.53635,0.64671,0.36316,1.38902,0.72055,0.78939,0.00098515,0.00098515,0.00098515
+5,3817.13,1.32709,0.60788,0.74776,0.84566,0.56372,0.67415,0.39056,1.33281,0.67538,0.78496,0.0009802,0.0009802,0.0009802
+6,4712.28,1.28936,0.5872,0.74673,0.84266,0.57438,0.68033,0.40443,1.27209,0.64319,0.78345,0.00097525,0.00097525,0.00097525
+7,5605.85,1.25984,0.5727,0.74524,0.84782,0.57,0.67373,0.38835,1.31188,0.63767,0.78474,0.0009703,0.0009703,0.0009703
+8,6478.77,1.23884,0.56163,0.74487,0.84269,0.57909,0.68077,0.39161,1.30807,0.631,0.78444,0.00096535,0.00096535,0.00096535
+9,7355.57,1.22429,0.55468,0.74353,0.84271,0.58262,0.68476,0.3964,1.3083,0.62192,0.78313,0.0009604,0.0009604,0.0009604
+10,8248.26,1.20836,0.5464,0.74268,0.85332,0.58195,0.6895,0.40035,1.29491,0.60687,0.78301,0.00095545,0.00095545,0.00095545
+11,9160.01,1.19649,0.54082,0.74272,0.84809,0.58179,0.68902,0.4039,1.28383,0.60786,0.78289,0.0009505,0.0009505,0.0009505
+12,10080.5,1.18664,0.5344,0.74255,0.84878,0.582,0.6914,0.4099,1.26084,0.60217,0.78158,0.00094555,0.00094555,0.00094555
+13,11021.8,1.17938,0.5308,0.74207,0.84738,0.58431,0.69285,0.40928,1.26915,0.60065,0.78187,0.0009406,0.0009406,0.0009406
+14,11957.6,1.16793,0.52703,0.74182,0.85144,0.58354,0.692,0.40857,1.27586,0.59912,0.78243,0.00093565,0.00093565,0.00093565
+15,12879.7,1.16249,0.52237,0.74152,0.85196,0.58473,0.69246,0.41108,1.26865,0.59603,0.78204,0.0009307,0.0009307,0.0009307
+16,13850.6,1.15473,0.51898,0.74159,0.85152,0.5851,0.69312,0.41148,1.27044,0.59652,0.78222,0.00092575,0.00092575,0.00092575
+17,14760.6,1.14727,0.51403,0.74096,0.85174,0.58578,0.69456,0.41141,1.27299,0.59684,0.78234,0.0009208,0.0009208,0.0009208
+18,15688.3,1.14333,0.51291,0.7403,0.85175,0.58622,0.69548,0.41184,1.27237,0.59619,0.7823,0.00091585,0.00091585,0.00091585
+19,16656.6,1.13888,0.51063,0.74074,0.85228,0.58636,0.69611,0.41199,1.27203,0.59565,0.78233,0.0009109,0.0009109,0.0009109
+20,17547.1,1.13396,0.50832,0.74022,0.85282,0.58659,0.69722,0.41239,1.2737,0.59554,0.78244,0.00090595,0.00090595,0.00090595
+21,18501,1.13001,0.50554,0.74079,0.85329,0.58701,0.6987,0.41363,1.27317,0.59504,0.78238,0.000901,0.000901,0.000901
+22,19360,1.12565,0.50435,0.7398,0.85328,0.58751,0.69963,0.41424,1.2746,0.59537,0.78246,0.00089605,0.00089605,0.00089605
+23,20292.4,1.11877,0.50094,0.74014,0.8547,0.58744,0.7011,0.41513,1.27621,0.5957,0.78251,0.0008911,0.0008911,0.0008911
+24,21207.3,1.1184,0.49949,0.73969,0.85441,0.58778,0.70225,0.41558,1.27726,0.59622,0.78256,0.00088615,0.00088615,0.00088615
+25,22166.8,1.11235,0.49746,0.74001,0.855,0.58808,0.70329,0.41627,1.27749,0.59641,0.78255,0.0008812,0.0008812,0.0008812
+26,23091.2,1.11046,0.49556,0.73924,0.85534,0.58834,0.70466,0.41665,1.28011,0.5978,0.7827,0.00087625,0.00087625,0.00087625
+27,24015.5,1.10799,0.49545,0.73951,0.85661,0.5887,0.70653,0.41796,1.28199,0.59877,0.78289,0.0008713,0.0008713,0.0008713
+28,24977.7,1.10307,0.49255,0.73928,0.85697,0.5894,0.70756,0.41889,1.28116,0.5989,0.78294,0.00086635,0.00086635,0.00086635
+29,25896.4,1.10171,0.49035,0.7399,0.8573,0.58964,0.70884,0.41901,1.28514,0.60023,0.78318,0.0008614,0.0008614,0.0008614
+30,26884.4,1.10104,0.49111,0.7392,0.85768,0.59027,0.71004,0.41939,1.28589,0.59916,0.78324,0.00085645,0.00085645,0.00085645
+31,27821.5,1.09736,0.48862,0.73946,0.85746,0.59113,0.71097,0.42024,1.28557,0.59891,0.78314,0.0008515,0.0008515,0.0008515
+32,28733.1,1.09599,0.48775,0.73911,0.85809,0.59126,0.71157,0.42121,1.28466,0.598,0.78303,0.00084655,0.00084655,0.00084655
+33,29706,1.09393,0.48622,0.73889,0.85828,0.59124,0.71156,0.42122,1.2855,0.59761,0.78301,0.0008416,0.0008416,0.0008416
+34,30760.6,1.09213,0.48571,0.73892,0.85874,0.59141,0.71226,0.4217,1.28475,0.59705,0.78299,0.00083665,0.00083665,0.00083665
+35,31740.2,1.08675,0.48405,0.73861,0.85966,0.59144,0.71291,0.42296,1.2837,0.59656,0.78303,0.0008317,0.0008317,0.0008317
+36,32605.9,1.08581,0.48359,0.73853,0.85936,0.59196,0.71396,0.42344,1.28431,0.59652,0.78307,0.00082675,0.00082675,0.00082675
+37,33541.1,1.0835,0.48112,0.73894,0.85966,0.5924,0.71531,0.42436,1.28276,0.59629,0.78294,0.0008218,0.0008218,0.0008218
+38,34450.5,1.07874,0.48046,0.73806,0.85953,0.59261,0.71569,0.42513,1.27985,0.59526,0.78279,0.00081685,0.00081685,0.00081685
+39,35388.2,1.07805,0.47898,0.73868,0.86018,0.59257,0.71596,0.4264,1.27597,0.59333,0.78266,0.0008119,0.0008119,0.0008119
+40,36385.5,1.07741,0.47892,0.73895,0.85977,0.59289,0.71615,0.42643,1.27493,0.59258,0.78264,0.00080695,0.00080695,0.00080695
+41,37396.2,1.07492,0.47629,0.73844,0.85985,0.59282,0.71633,0.42756,1.27334,0.59238,0.7827,0.000802,0.000802,0.000802
+42,38336.4,1.07379,0.47665,0.73838,0.86076,0.59259,0.71672,0.42822,1.27189,0.59201,0.78263,0.00079705,0.00079705,0.00079705
+43,39303.9,1.07174,0.47517,0.7387,0.86162,0.59276,0.71719,0.42859,1.27001,0.59113,0.78267,0.0007921,0.0007921,0.0007921
+44,40324.3,1.07322,0.4763,0.73838,0.86297,0.59271,0.71744,0.42976,1.26764,0.59017,0.78261,0.00078715,0.00078715,0.00078715
+45,41422.2,1.06913,0.47481,0.7379,0.86292,0.59329,0.7179,0.43054,1.2653,0.58916,0.78264,0.0007822,0.0007822,0.0007822
+46,42420.1,1.06649,0.47469,0.73819,0.8625,0.59358,0.71816,0.43129,1.26336,0.58825,0.78259,0.00077725,0.00077725,0.00077725
+47,43397.9,1.06743,0.47507,0.73795,0.86227,0.59341,0.71781,0.43132,1.26294,0.58816,0.78257,0.0007723,0.0007723,0.0007723
+48,44368.4,1.06518,0.47236,0.73805,0.86187,0.59335,0.7178,0.43179,1.26079,0.58801,0.78245,0.00076735,0.00076735,0.00076735
+49,45305.6,1.06516,0.47263,0.73795,0.86119,0.59339,0.7173,0.43038,1.26234,0.5882,0.78253,0.0007624,0.0007624,0.0007624
+50,46243.3,1.06248,0.47116,0.73813,0.86201,0.59264,0.71756,0.4314,1.25966,0.58834,0.78241,0.00075745,0.00075745,0.00075745
+51,47137.6,1.06006,0.47007,0.73811,0.86184,0.5926,0.71724,0.43097,1.25968,0.58829,0.78252,0.0007525,0.0007525,0.0007525
+52,48148.9,1.0573,0.46921,0.7378,0.86197,0.59251,0.71712,0.43023,1.26029,0.5883,0.78264,0.00074755,0.00074755,0.00074755
+53,49047.6,1.05948,0.46972,0.73794,0.86222,0.59246,0.71669,0.4288,1.26147,0.58763,0.78275,0.0007426,0.0007426,0.0007426
+54,50003.7,1.05605,0.46839,0.73764,0.86138,0.59297,0.71709,0.42863,1.26179,0.58758,0.78277,0.00073765,0.00073765,0.00073765
+55,50920.2,1.05369,0.46685,0.73762,0.86218,0.59249,0.71732,0.42842,1.26457,0.58879,0.78306,0.0007327,0.0007327,0.0007327
+56,51819.8,1.05221,0.46597,0.73756,0.86184,0.59248,0.71718,0.42826,1.26547,0.58888,0.78324,0.00072775,0.00072775,0.00072775
+57,52778.7,1.05184,0.46607,0.73766,0.86219,0.59243,0.71702,0.42813,1.26579,0.58908,0.78327,0.0007228,0.0007228,0.0007228
+58,53745.3,1.05082,0.46603,0.73738,0.86305,0.59192,0.717,0.42843,1.26523,0.58902,0.78331,0.00071785,0.00071785,0.00071785
+59,54734.8,1.04964,0.46449,0.73742,0.86359,0.59146,0.71713,0.42905,1.26538,0.58903,0.7835,0.0007129,0.0007129,0.0007129
+60,55744.6,1.04881,0.4646,0.73761,0.86311,0.59145,0.71715,0.42874,1.26711,0.58921,0.78361,0.00070795,0.00070795,0.00070795
+61,56712.6,1.04673,0.46278,0.73797,0.86292,0.5914,0.71733,0.42865,1.26763,0.5895,0.78368,0.000703,0.000703,0.000703
+62,57635,1.04612,0.46248,0.73763,0.86188,0.59147,0.71735,0.42877,1.26679,0.58916,0.7837,0.00069805,0.00069805,0.00069805
+63,58639,1.04511,0.46204,0.73736,0.86158,0.59145,0.71748,0.42837,1.2681,0.58965,0.78382,0.0006931,0.0006931,0.0006931
+64,59538.1,1.04695,0.4633,0.7374,0.86094,0.59143,0.71753,0.42772,1.27074,0.59001,0.78404,0.00068815,0.00068815,0.00068815
+65,60483.4,1.04596,0.4622,0.73738,0.86003,0.5915,0.71743,0.42744,1.26962,0.5898,0.78398,0.0006832,0.0006832,0.0006832
+66,61480.7,1.04433,0.4623,0.73698,0.8599,0.59133,0.71725,0.42697,1.27098,0.59032,0.78409,0.00067825,0.00067825,0.00067825
+67,62443.2,1.04174,0.46117,0.7373,0.85955,0.59132,0.71707,0.42668,1.27073,0.59001,0.78415,0.0006733,0.0006733,0.0006733
+68,63391.3,1.04008,0.46057,0.73727,0.85926,0.59167,0.7172,0.42672,1.26904,0.58894,0.78412,0.00066835,0.00066835,0.00066835
+69,64349.8,1.0404,0.46023,0.73744,0.8588,0.59206,0.71767,0.42681,1.27067,0.58929,0.7843,0.0006634,0.0006634,0.0006634
+70,65354.4,1.03638,0.4588,0.73739,0.85895,0.5922,0.71774,0.42677,1.27193,0.58964,0.78437,0.00065845,0.00065845,0.00065845
+71,66276.9,1.03584,0.45816,0.73709,0.85869,0.59222,0.71743,0.42658,1.27146,0.5896,0.78442,0.0006535,0.0006535,0.0006535
+72,67253.4,1.03837,0.4582,0.73715,0.85864,0.59213,0.71766,0.42662,1.27271,0.58969,0.78456,0.00064855,0.00064855,0.00064855
+73,68182.5,1.03438,0.45738,0.73725,0.8596,0.59187,0.71815,0.42681,1.27374,0.58999,0.78458,0.0006436,0.0006436,0.0006436
+74,69137,1.03597,0.45786,0.7369,0.86006,0.59241,0.71872,0.42775,1.27188,0.58967,0.78436,0.00063865,0.00063865,0.00063865
+75,70081.1,1.03436,0.45652,0.73676,0.86105,0.59253,0.71907,0.42807,1.27283,0.58996,0.78442,0.0006337,0.0006337,0.0006337
+76,71137.3,1.03396,0.45593,0.73722,0.86188,0.59273,0.71947,0.42855,1.27351,0.59011,0.7844,0.00062875,0.00062875,0.00062875
+77,72138.3,1.03367,0.45615,0.73681,0.86171,0.59299,0.71939,0.42833,1.27501,0.59028,0.78455,0.0006238,0.0006238,0.0006238
+78,73135.8,1.03212,0.45593,0.73677,0.86149,0.59285,0.71918,0.42722,1.27964,0.59159,0.78491,0.00061885,0.00061885,0.00061885
+79,74122.1,1.0303,0.45532,0.73731,0.86198,0.59288,0.71911,0.42744,1.27849,0.59115,0.78488,0.0006139,0.0006139,0.0006139
+80,75098.2,1.03031,0.45587,0.73735,0.86241,0.59323,0.71956,0.4282,1.2752,0.59024,0.78469,0.00060895,0.00060895,0.00060895
+81,76067.1,1.02756,0.45412,0.73639,0.86239,0.59284,0.71939,0.42786,1.27612,0.59031,0.78477,0.000604,0.000604,0.000604
+82,77026.9,1.02814,0.4541,0.73714,0.86166,0.5932,0.7196,0.42797,1.27736,0.59061,0.78491,0.00059905,0.00059905,0.00059905
+83,78037.1,1.02686,0.45258,0.73663,0.86208,0.59277,0.71978,0.42826,1.27723,0.59115,0.78496,0.0005941,0.0005941,0.0005941
+84,78997.6,1.02763,0.45326,0.73653,0.86215,0.59249,0.71995,0.42836,1.27747,0.59164,0.78494,0.00058915,0.00058915,0.00058915
+85,79925.5,1.02697,0.45207,0.73666,0.8622,0.59221,0.71984,0.4283,1.27819,0.59187,0.78512,0.0005842,0.0005842,0.0005842
+86,80886.2,1.02473,0.45253,0.73638,0.86175,0.59258,0.72004,0.42852,1.27797,0.59178,0.78518,0.00057925,0.00057925,0.00057925
+87,81811.8,1.02297,0.4501,0.73671,0.86142,0.59267,0.72022,0.42861,1.27827,0.59236,0.78528,0.0005743,0.0005743,0.0005743
+88,82914,1.02263,0.451,0.73627,0.86116,0.59264,0.72057,0.42855,1.28018,0.59284,0.78539,0.00056935,0.00056935,0.00056935

custom_LP_detect/yolo_exp.ipynb

@@ -0,0 +1,685 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a7676704",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from ultralytics import YOLO\n",
+    "\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3e94066a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "torch.cuda.is_available()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "99b0442c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "New https://pypi.org/project/ultralytics/8.3.228 available 😃 Update with 'pip install -U ultralytics'\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, augment=False, auto_augment=randaugment, batch=-1, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=/home/cuuva/experiment/custom_LP_detect/custom_LP.yaml, degrees=0.0, deterministic=True, device=0, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, epochs=200, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=0.2, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.001, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolov8n.pt, momentum=0.937, mosaic=1.0, multi_scale=False, name=epo_200_frac_0_22, nbs=64, nms=False, opset=None, optimize=False, optimizer=AdamW, overlap_mask=True, patience=40, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=lp_detect, rect=False, resume=False, retina_masks=False, save=True, save_conf=False, save_crop=False, save_dir=/home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n",
+      "Overriding model.yaml nc=80 with nc=1\n",
+      "\n",
+      "                   from  n    params  module                                       arguments                     \n",
+      "  0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]                 \n",
+      "  1                  -1  1      4672  ultralytics.nn.modules.conv.Conv             [16, 32, 3, 2]                \n",
+      "  2                  -1  1      7360  ultralytics.nn.modules.block.C2f             [32, 32, 1, True]             \n",
+      "  3                  -1  1     18560  ultralytics.nn.modules.conv.Conv             [32, 64, 3, 2]                \n",
+      "  4                  -1  2     49664  ultralytics.nn.modules.block.C2f             [64, 64, 2, True]             \n",
+      "  5                  -1  1     73984  ultralytics.nn.modules.conv.Conv             [64, 128, 3, 2]               \n",
+      "  6                  -1  2    197632  ultralytics.nn.modules.block.C2f             [128, 128, 2, True]           \n",
+      "  7                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]              \n",
+      "  8                  -1  1    460288  ultralytics.nn.modules.block.C2f             [256, 256, 1, True]           \n",
+      "  9                  -1  1    164608  ultralytics.nn.modules.block.SPPF            [256, 256, 5]                 \n",
+      " 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 12                  -1  1    148224  ultralytics.nn.modules.block.C2f             [384, 128, 1]                 \n",
+      " 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 15                  -1  1     37248  ultralytics.nn.modules.block.C2f             [192, 64, 1]                  \n",
+      " 16                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]                \n",
+      " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 18                  -1  1    123648  ultralytics.nn.modules.block.C2f             [192, 128, 1]                 \n",
+      " 19                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]              \n",
+      " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 21                  -1  1    493056  ultralytics.nn.modules.block.C2f             [384, 256, 1]                 \n",
+      " 22        [15, 18, 21]  1    751507  ultralytics.nn.modules.head.Detect           [1, [64, 128, 256]]           \n",
+      "Model summary: 129 layers, 3,011,043 parameters, 3,011,027 gradients, 8.2 GFLOPs\n",
+      "\n",
+      "Transferred 319/355 items from pretrained weights\n",
+      "Freezing layer 'model.22.dfl.conv.weight'\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 1415.2±186.1 MB/s, size: 1748.6 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/labels/license_plate/ar01_01.cache... 160269 images, 0 backgrounds, 2 corrupt: 100% ━━━━━━━━━━━━ 160271/160271 514.3Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-220930_08_AR01_01_N0023.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-221011_13_AR01_01_N4945.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-221019_12_AR01_01_N5133.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-221019_14_AR01_01_N0089.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar03_03/C-221105_17_AR03_03_N0282.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar03_03/C-221109_14_AR03_03_N0673.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar04_04/C-221022_14_AR04_04_N0674.jpg: 2 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar09_01/C-220807_15_AR09_01_N0514.jpg: ignoring corrupt image/label: image file is truncated (107 bytes not processed)\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/cr01_02/C-220827_16_CR01_02_N0098.jpg: ignoring corrupt image/label: image file is truncated (96 bytes not processed)\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mComputing optimal batch size for imgsz=640 at 60.0% CUDA memory utilization.\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mCUDA:0 (NVIDIA GeForce RTX 5090) 31.33G total, 0.15G reserved, 0.05G allocated, 31.13G free\n",
+      "      Params      GFLOPs  GPU_mem (GB)  forward (ms) backward (ms)                   input                  output\n",
+      "     3011043       8.194         3.456         31.09         193.1        (1, 3, 640, 640)                    list\n",
+      "     3011043       16.39         3.997         4.507         23.43        (2, 3, 640, 640)                    list\n",
+      "     3011043       32.78         4.270          5.17         24.49        (4, 3, 640, 640)                    list\n",
+      "     3011043       65.55         4.979         5.493         31.44        (8, 3, 640, 640)                    list\n",
+      "     3011043       131.1         6.201         7.781         41.38       (16, 3, 640, 640)                    list\n",
+      "     3011043       262.2         5.014         15.01         55.64       (32, 3, 640, 640)                    list\n",
+      "     3011043       524.4        10.863         31.73         105.9       (64, 3, 640, 640)                    list\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mUsing batch-size 135 for CUDA:0 19.16G/31.33G (61%) ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 1182.9±337.0 MB/s, size: 1333.9 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/labels/license_plate/ar01_01.cache... 160269 images, 0 backgrounds, 2 corrupt: 100% ━━━━━━━━━━━━ 160271/160271 317.1Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-220930_08_AR01_01_N0023.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-221011_13_AR01_01_N4945.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-221019_12_AR01_01_N5133.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar01_01/C-221019_14_AR01_01_N0089.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar03_03/C-221105_17_AR03_03_N0282.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar03_03/C-221109_14_AR03_03_N0673.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar04_04/C-221022_14_AR04_04_N0674.jpg: 2 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/ar09_01/C-220807_15_AR09_01_N0514.jpg: ignoring corrupt image/label: image file is truncated (107 bytes not processed)\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Training/images/license_plate/cr01_02/C-220827_16_CR01_02_N0098.jpg: ignoring corrupt image/label: image file is truncated (96 bytes not processed)\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 1014.6±261.7 MB/s, size: 1776.7 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/labels/license_plate/ar01_01.cache... 52168 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 52168/52168 98.1Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/images/license_plate/ar01_01/C-221030_13_AR01_01_N0451.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/images/license_plate/sr02_01/C-220921_13_SR02_01_N0664.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/images/license_plate/sr08_01/C-221026_17_SR08_01_N0368.jpg: 3 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/images/license_plate/sr10_01/C-221111_14_SR10_01_N2786.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/images/license_plate/sr10_01/C-221112_10_SR10_01_N3102.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/CCTV_car_or_licenseplate/data/Validation/images/license_plate/sr10_01/C-221112_13_SR10_01_N1269.jpg: 1 duplicate labels removed\n",
+      "Plotting labels to /home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22/labels.jpg... \n",
+      "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.001, momentum=0.937) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0010546875), 63 bias(decay=0.0)\n",
+      "Image sizes 640 train, 640 val\n",
+      "Using 8 dataloader workers\n",
+      "Logging results to \u001b[1m/home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22\u001b[0m\n",
+      "Starting training for 200 epochs...\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      1/200      18.1G      2.084      2.448     0.8108        125        640: 100% ━━━━━━━━━━━━ 1188/1188 2.1it/s 9:14<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.7sss\n",
+      "                   all      52168     159183      0.719      0.475       0.53      0.234\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      2/200        18G      1.587     0.7441     0.7597        115        640: 100% ━━━━━━━━━━━━ 1188/1188 2.2it/s 8:56<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.7sss\n",
+      "                   all      52168     159183      0.817      0.527      0.613      0.329\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      3/200        18G      1.474     0.6842     0.7541        108        640: 100% ━━━━━━━━━━━━ 1188/1188 1.7it/s 11:43<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:420.7sss\n",
+      "                   all      52168     159183      0.809      0.533      0.608      0.326\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      4/200        18G      1.389     0.6393     0.7508        123        640: 100% ━━━━━━━━━━━━ 1188/1188 1.7it/s 11:40<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:370.6sss\n",
+      "                   all      52168     159183      0.836      0.536      0.647      0.363\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      5/200        18G      1.327     0.6079     0.7478        100        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 12:49<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:420.5sss\n",
+      "                   all      52168     159183      0.846      0.564      0.674      0.391\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      6/200        18G      1.289     0.5872     0.7467        130        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:20<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:300.6sss\n",
+      "                   all      52168     159183      0.843      0.574       0.68      0.404\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      7/200        18G       1.26     0.5727     0.7452        133        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:09<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.6sss\n",
+      "                   all      52168     159183      0.848       0.57      0.674      0.388\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      8/200        18G      1.239     0.5616     0.7449         98        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 12:50<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.7sss\n",
+      "                   all      52168     159183      0.843      0.579      0.681      0.392\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      9/200        18G      1.224     0.5547     0.7435        119        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 12:51<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:380.6sss\n",
+      "                   all      52168     159183      0.843      0.583      0.685      0.396\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     10/200        18G      1.208     0.5464     0.7427        107        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:12<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.7sss\n",
+      "                   all      52168     159183      0.853      0.582      0.689        0.4\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     11/200        18G      1.196     0.5408     0.7427        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:22<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:410.7sss\n",
+      "                   all      52168     159183      0.848      0.582      0.689      0.404\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     12/200        18G      1.187     0.5344     0.7425        104        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:36<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:380.6sss\n",
+      "                   all      52168     159183      0.849      0.582      0.691       0.41\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     13/200        18G      1.179     0.5308     0.7421        122        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:55<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:380.7sss\n",
+      "                   all      52168     159183      0.847      0.584      0.693      0.409\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     14/200        18G      1.168      0.527     0.7418        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:56<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:330.6sss\n",
+      "                   all      52168     159183      0.851      0.584      0.692      0.409\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     15/200        18G      1.162     0.5224     0.7415        106        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:42<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.5sss\n",
+      "                   all      52168     159183      0.852      0.585      0.692      0.411\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     16/200        18G      1.155      0.519     0.7416        125        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:38<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:270.5sss\n",
+      "                   all      52168     159183      0.852      0.585      0.693      0.411\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     17/200        18G      1.147      0.514      0.741        106        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:29<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.852      0.586      0.695      0.411\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     18/200        18G      1.143     0.5129     0.7403        147        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:47<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.852      0.586      0.695      0.412\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     19/200        18G      1.139     0.5106     0.7407        135        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:24<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:390.6sss\n",
+      "                   all      52168     159183      0.852      0.586      0.696      0.412\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     20/200        18G      1.134     0.5083     0.7402        106        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:08<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.5sss\n",
+      "                   all      52168     159183      0.853      0.587      0.697      0.412\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     21/200        18G       1.13     0.5055     0.7408        113        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:10<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.7sss\n",
+      "                   all      52168     159183      0.853      0.587      0.699      0.414\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     22/200        18G      1.126     0.5043     0.7398        134        640: 100% ━━━━━━━━━━━━ 1188/1188 1.6it/s 12:41<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:300.7sss\n",
+      "                   all      52168     159183      0.853      0.588        0.7      0.414\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     23/200        18G      1.119     0.5009     0.7401        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:51<0.9s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.5sss\n",
+      "                   all      52168     159183      0.855      0.587      0.701      0.415\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     24/200        18G      1.118     0.4995     0.7397        120        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:39<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:300.6sss\n",
+      "                   all      52168     159183      0.854      0.588      0.702      0.416\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     25/200        18G      1.112     0.4975       0.74        124        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:17<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.855      0.588      0.703      0.416\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     26/200        18G       1.11     0.4956     0.7392        109        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:45<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.6sss\n",
+      "                   all      52168     159183      0.855      0.588      0.705      0.417\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     27/200        18G      1.108     0.4955     0.7395        116        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:42<0.9s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.857      0.589      0.707      0.418\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     28/200        18G      1.103     0.4925     0.7393        106        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:22<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.857      0.589      0.708      0.419\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     29/200        18G      1.102     0.4903     0.7399        101        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:36<0.9s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:370.6sss\n",
+      "                   all      52168     159183      0.857       0.59      0.709      0.419\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     30/200        18G      1.101     0.4911     0.7392        116        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:49<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.6sss\n",
+      "                   all      52168     159183      0.858       0.59       0.71      0.419\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     31/200        18G      1.097     0.4886     0.7395        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:54<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.7sss\n",
+      "                   all      52168     159183      0.857      0.591      0.711       0.42\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     32/200        18G      1.096     0.4877     0.7391         90        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:41<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:270.5sss\n",
+      "                   all      52168     159183      0.858      0.591      0.712      0.421\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     33/200        18G      1.094     0.4862     0.7389        122        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:31<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.858      0.591      0.712      0.421\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     34/200        18G      1.092     0.4857     0.7389        126        640: 100% ━━━━━━━━━━━━ 1188/1188 1.2it/s 15:58<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.6sss\n",
+      "                   all      52168     159183      0.859      0.591      0.712      0.422\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     35/200        18G      1.087      0.484     0.7386        102        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:35<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:370.6sss\n",
+      "                   all      52168     159183       0.86      0.591      0.713      0.423\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     36/200        18G      1.086     0.4836     0.7385        117        640: 100% ━━━━━━━━━━━━ 1188/1188 1.6it/s 12:42<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.6sss\n",
+      "                   all      52168     159183      0.859      0.592      0.714      0.423\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     37/200        18G      1.084     0.4811     0.7389         97        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:46<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:430.6sss\n",
+      "                   all      52168     159183       0.86      0.592      0.715      0.424\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     38/200        18G      1.079     0.4805     0.7381        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:34<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:310.6sss\n",
+      "                   all      52168     159183       0.86      0.593      0.716      0.425\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     39/200      18.4G      1.078      0.479     0.7387        110        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:02<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.5sss\n",
+      "                   all      52168     159183       0.86      0.593      0.716      0.426\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     40/200        18G      1.077     0.4789      0.739        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:05<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:290.6sss\n",
+      "                   all      52168     159183       0.86      0.593      0.716      0.426\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     41/200        18G      1.075     0.4763     0.7384        107        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:10<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:330.6sss\n",
+      "                   all      52168     159183       0.86      0.593      0.716      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     42/200        18G      1.074     0.4767     0.7384         98        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:02<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:300.6sss\n",
+      "                   all      52168     159183      0.861      0.593      0.717      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     43/200        18G      1.072     0.4752     0.7387         90        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:24<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:380.6sss\n",
+      "                   all      52168     159183      0.862      0.593      0.717      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     44/200        18G      1.073     0.4763     0.7384        102        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:18<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:380.6sss\n",
+      "                   all      52168     159183      0.863      0.593      0.717       0.43\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     45/200        18G      1.069     0.4748     0.7379        118        640: 100% ━━━━━━━━━━━━ 1188/1188 1.2it/s 16:39<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.7sss\n",
+      "                   all      52168     159183      0.863      0.593      0.718      0.431\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     46/200        18G      1.066     0.4747     0.7382         91        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:58<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:290.6sss\n",
+      "                   all      52168     159183      0.863      0.594      0.718      0.431\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     47/200        18G      1.067     0.4751      0.738         95        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:33<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:400.8sss\n",
+      "                   all      52168     159183      0.862      0.593      0.718      0.431\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     48/200        18G      1.065     0.4724      0.738        130        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:33<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:310.5sss\n",
+      "                   all      52168     159183      0.862      0.593      0.718      0.432\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     49/200        18G      1.065     0.4726     0.7379        126        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:53<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:400.6sss\n",
+      "                   all      52168     159183      0.861      0.593      0.717       0.43\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     50/200        18G      1.062     0.4712     0.7381        113        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:60<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:330.6sss\n",
+      "                   all      52168     159183      0.862      0.593      0.718      0.431\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     51/200        18G       1.06     0.4701     0.7381        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:09<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:370.5sss\n",
+      "                   all      52168     159183      0.862      0.593      0.717      0.431\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     52/200        18G      1.057     0.4692     0.7378        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:09<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.6sss\n",
+      "                   all      52168     159183      0.862      0.593      0.717       0.43\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     53/200        18G      1.059     0.4697     0.7379        116        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:18<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.6sss\n",
+      "                   all      52168     159183      0.862      0.592      0.717      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     54/200        18G      1.056     0.4684     0.7376        113        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:22<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:300.6sss\n",
+      "                   all      52168     159183      0.861      0.593      0.717      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     55/200        18G      1.054     0.4668     0.7376        108        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:37<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.8sss\n",
+      "                   all      52168     159183      0.862      0.592      0.717      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     56/200        18G      1.052      0.466     0.7376        127        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:25<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.6sss\n",
+      "                   all      52168     159183      0.862      0.592      0.717      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     57/200        18G      1.052     0.4661     0.7377        105        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:07<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.8it/s 1:460.6sss\n",
+      "                   all      52168     159183      0.862      0.592      0.717      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     58/200        18G      1.051      0.466     0.7374        112        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:27<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:330.7sss\n",
+      "                   all      52168     159183      0.863      0.592      0.717      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     59/200        18G       1.05     0.4645     0.7374         92        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:48<0.9s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.864      0.591      0.717      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     60/200        18G      1.049     0.4646     0.7376        116        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:09<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:330.6sss\n",
+      "                   all      52168     159183      0.863      0.591      0.717      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     61/200        18G      1.047     0.4628      0.738        122        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:25<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.6sss\n",
+      "                   all      52168     159183      0.863      0.591      0.717      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     62/200        18G      1.046     0.4625     0.7376        101        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:42<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:350.6sss\n",
+      "                   all      52168     159183      0.862      0.591      0.717      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     63/200        18G      1.045      0.462     0.7374        126        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:60<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.5sss\n",
+      "                   all      52168     159183      0.862      0.591      0.717      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     64/200        18G      1.047     0.4633     0.7374        110        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:19<0.9s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.4sss\n",
+      "                   all      52168     159183      0.861      0.591      0.718      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     65/200        18G      1.046     0.4622     0.7374        126        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:07<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.5sss\n",
+      "                   all      52168     159183       0.86      0.592      0.717      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     66/200        18G      1.044     0.4623      0.737        103        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:59<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:330.6sss\n",
+      "                   all      52168     159183       0.86      0.591      0.717      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     67/200        18G      1.042     0.4612     0.7373        113        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:20<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:370.5sss\n",
+      "                   all      52168     159183       0.86      0.591      0.717      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     68/200        18G       1.04     0.4606     0.7373        111        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:09<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.7sss\n",
+      "                   all      52168     159183      0.859      0.592      0.717      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     69/200        18G       1.04     0.4602     0.7374        107        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:13<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:410.7sss\n",
+      "                   all      52168     159183      0.859      0.592      0.718      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     70/200        18G      1.036     0.4588     0.7374        122        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:04<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:340.7sss\n",
+      "                   all      52168     159183      0.859      0.592      0.718      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     71/200        18G      1.036     0.4582     0.7371         93        640: 100% ━━━━━━━━━━━━ 1188/1188 1.5it/s 13:38<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:400.6sss\n",
+      "                   all      52168     159183      0.859      0.592      0.717      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     72/200        18G      1.038     0.4582     0.7371        119        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:37<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.5sss\n",
+      "                   all      52168     159183      0.859      0.592      0.718      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     73/200        18G      1.034     0.4574     0.7373         93        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:48<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.6sss\n",
+      "                   all      52168     159183       0.86      0.592      0.718      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     74/200        18G      1.036     0.4579     0.7369        103        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:12<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:350.6sss\n",
+      "                   all      52168     159183       0.86      0.592      0.719      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     75/200        18G      1.034     0.4565     0.7368        112        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:55<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:420.6sss\n",
+      "                   all      52168     159183      0.861      0.593      0.719      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     76/200        18G      1.034     0.4559     0.7372        122        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:49<1.0s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:400.6sss\n",
+      "                   all      52168     159183      0.862      0.593      0.719      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     77/200        18G      1.034     0.4562     0.7368        117        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:55<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 1.9it/s 1:420.6sss\n",
+      "                   all      52168     159183      0.862      0.593      0.719      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     78/200        18G      1.032     0.4559     0.7368        122        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:59<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:310.6sss\n",
+      "                   all      52168     159183      0.861      0.593      0.719      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     79/200        18G       1.03     0.4553     0.7373        112        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:49<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:310.6sss\n",
+      "                   all      52168     159183      0.862      0.593      0.719      0.427\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     80/200        18G       1.03     0.4559     0.7374        131        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 14:44<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:290.5sss\n",
+      "                   all      52168     159183      0.862      0.593       0.72      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     81/200        18G      1.028     0.4541     0.7364        105        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:33<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.7sss\n",
+      "                   all      52168     159183      0.862      0.593      0.719      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     82/200        18G      1.028     0.4541     0.7371        110        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:25<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.2it/s 1:300.6sss\n",
+      "                   all      52168     159183      0.862      0.593       0.72      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     83/200        18G      1.027     0.4526     0.7366         98        640: 100% ━━━━━━━━━━━━ 1188/1188 1.3it/s 15:05<0.9s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:390.6sss\n",
+      "                   all      52168     159183      0.862      0.593       0.72      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     84/200        18G      1.028     0.4533     0.7365         99        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:21<0.3s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.7sss\n",
+      "                   all      52168     159183      0.862      0.592       0.72      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     85/200        18G      1.027     0.4521     0.7367        101        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:48<0.9s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.0it/s 1:360.6sss\n",
+      "                   all      52168     159183      0.862      0.592       0.72      0.428\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     86/200        18G      1.025     0.4525     0.7364        108        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 14:24<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.6sss\n",
+      "                   all      52168     159183      0.862      0.593       0.72      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     87/200        18G      1.023     0.4501     0.7367         91        640: 100% ━━━━━━━━━━━━ 1188/1188 1.4it/s 13:48<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:310.5sss\n",
+      "                   all      52168     159183      0.861      0.593       0.72      0.429\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     88/200        18G      1.023      0.451     0.7363        129        640: 100% ━━━━━━━━━━━━ 1188/1188 1.2it/s 16:46<0.8s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.1it/s 1:320.7sss\n",
+      "                   all      52168     159183      0.861      0.593      0.721      0.429\n",
+      "\u001b[34m\u001b[1mEarlyStopping: \u001b[0mTraining stopped early as no improvement observed in last 40 epochs. Best results observed at epoch 48, best model saved as best.pt.\n",
+      "To update EarlyStopping(patience=40) pass a new patience value, i.e. `patience=300` or use `patience=0` to disable EarlyStopping.\n",
+      "\n",
+      "88 epochs completed in 23.032 hours.\n",
+      "Optimizer stripped from /home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22/weights/last.pt, 6.2MB\n",
+      "Optimizer stripped from /home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22/weights/best.pt, 6.2MB\n",
+      "\n",
+      "Validating /home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22/weights/best.pt...\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "Model summary (fused): 72 layers, 3,005,843 parameters, 0 gradients, 8.1 GFLOPs\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 194/194 2.3it/s 1:230.4sss\n",
+      "                   all      52168     159183      0.862      0.593      0.718      0.431\n",
+      "Speed: 0.0ms preprocess, 0.2ms inference, 0.0ms loss, 0.3ms postprocess per image\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load a pretrained YOLO11n model\n",
+    "model = YOLO(\"yolov8n.pt\")\n",
+    "\n",
+    "train_results = model.train(\n",
+    "    data=\"/home/cuuva/experiment/custom_LP_detect/custom_LP.yaml\",\n",
+    "    epochs=200,\n",
+    "    imgsz=640,\n",
+    "    batch= -1,\n",
+    "    device=\"cuda\",\n",
+    "    optimizer = 'AdamW',\n",
+    "    lr0 = 0.001,\n",
+    "    patience = 40,\n",
+    "    project = 'lp_detect',\n",
+    "    name = 'epo_200_frac_0_2',\n",
+    "    fraction = 0.2\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "88d6a47e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32109MiB)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "YOLOv8n summary (fused): 72 layers, 3,005,843 parameters, 0 gradients, 8.1 GFLOPs\n",
+      "\n",
+      "\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from '/home/cuuva/experiment/custom_LP_detect/license_plate_detector.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 5, 8400) (6.0 MB)\n",
+      "\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m starting export with onnx 1.19.1 opset 20...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m slimming with onnxslim 0.1.71...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m export success ✅ 0.3s, saved as '/home/cuuva/experiment/custom_LP_detect/license_plate_detector.onnx' (11.7 MB)\n",
+      "\n",
+      "Export complete (0.4s)\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/custom_LP_detect\u001b[0m\n",
+      "Predict:         yolo predict task=detect model=/home/cuuva/experiment/custom_LP_detect/license_plate_detector.onnx imgsz=640  \n",
+      "Validate:        yolo val task=detect model=/home/cuuva/experiment/custom_LP_detect/license_plate_detector.onnx imgsz=640 data=config.yaml  \n",
+      "Visualize:       https://netron.app\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/home/cuuva/experiment/custom_LP_detect/license_plate_detector.onnx'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# model = YOLO(\"/home/cuuva/experiment/custom_LP_detect/lp_detect/epo_200_frac_0_22/weights/best_lp_detect.pt\")\n",
+    "model = YOLO(\"/home/cuuva/experiment/custom_LP_detect/license_plate_detector.pt\")\n",
+    "model.export(format=\"onnx\", imgsz=640, device=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0084e5f9",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "1stagedetect",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

fashion_yolo/aihub_dataset_eda.ipynb

@@ -0,0 +1,156 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "fc523237",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "================= CLASS STATISTICS =================\n",
+      "\n",
+      "📁 Training Dataset\n",
+      "   [0] BLOUSE      👉  9014 개\n",
+      "   [1] COAT        👉  9949 개\n",
+      "   [2] DRESS       👉  10173 개\n",
+      "   [3] JACKET      👉  10466 개\n",
+      "   [4] JUMPER      👉  21893 개\n",
+      "   [5] PANTS       👉  69937 개\n",
+      "   [6] SHIRTS      👉  13438 개\n",
+      "   [7] SKIRT       👉  18156 개\n",
+      "   [8] TSHIRTS     👉  45025 개\n",
+      "\n",
+      "\n",
+      "📁 Validation Dataset\n",
+      "   [0] BLOUSE      👉  1127 개\n",
+      "   [1] COAT        👉  1242 개\n",
+      "   [2] DRESS       👉  1270 개\n",
+      "   [3] JACKET      👉  1309 개\n",
+      "   [4] JUMPER      👉  2737 개\n",
+      "   [5] PANTS       👉  8741 개\n",
+      "   [6] SHIRTS      👉  1681 개\n",
+      "   [7] SKIRT       👉  2269 개\n",
+      "   [8] TSHIRTS     👉  5624 개\n",
+      "\n",
+      "\n",
+      "=============== TOTAL SUMMARY ===============\n",
+      "\n",
+      "   [0] BLOUSE      👉  10141 total\n",
+      "   [1] COAT        👉  11191 total\n",
+      "   [2] DRESS       👉  11443 total\n",
+      "   [3] JACKET      👉  11775 total\n",
+      "   [4] JUMPER      👉  24630 total\n",
+      "   [5] PANTS       👉  78678 total\n",
+      "   [6] SHIRTS      👉  15119 total\n",
+      "   [7] SKIRT       👉  20425 total\n",
+      "   [8] TSHIRTS     👉  50649 total\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from collections import defaultdict\n",
+    "\n",
+    "# ---- CLASS MAP (사용자가 정의한 클래스) ----\n",
+    "CLASS_MAP = {\n",
+    "    \"0\": \"BLOUSE\",\n",
+    "    \"1\": \"COAT\",\n",
+    "    \"2\": \"DRESS\",\n",
+    "    \"3\": \"JACKET\",\n",
+    "    \"4\": \"JUMPER\",\n",
+    "    \"5\": \"PANTS\",\n",
+    "    \"6\": \"SHIRTS\",\n",
+    "    \"7\": \"SKIRT\",\n",
+    "    \"8\": \"TSHIRTS\"\n",
+    "}\n",
+    "\n",
+    "# ---- 데이터 경로 ----\n",
+    "DATASETS = {\n",
+    "    \"Training\": \"/home/cuuva/aihub_car/clothes_dataset/Training/labels_txt\",\n",
+    "    \"Validation\": \"/home/cuuva/aihub_car/clothes_dataset/Validation/labels_txt\"\n",
+    "}\n",
+    "\n",
+    "\n",
+    "def count_classes(path):\n",
+    "    class_count = defaultdict(int)\n",
+    "\n",
+    "    for root, _, files in os.walk(path):\n",
+    "        for file in files:\n",
+    "            if file.endswith(\".txt\"):\n",
+    "                file_path = os.path.join(root, file)\n",
+    "\n",
+    "                with open(file_path, \"r\") as f:\n",
+    "                    lines = f.readlines()\n",
+    "\n",
+    "                for line in lines:\n",
+    "                    if line.strip():\n",
+    "                        class_id = line.split()[0]\n",
+    "                        class_count[class_id] += 1\n",
+    "\n",
+    "    # 정렬\n",
+    "    return dict(sorted(class_count.items(), key=lambda x: int(x[0])))\n",
+    "\n",
+    "\n",
+    "# ---- 실행 ----\n",
+    "results = {}\n",
+    "for name, path in DATASETS.items():\n",
+    "    results[name] = count_classes(path)\n",
+    "\n",
+    "print(\"\\n================= CLASS STATISTICS =================\\n\")\n",
+    "\n",
+    "# ---- 상세 출력 ----\n",
+    "for dataset_name, counts in results.items():\n",
+    "    print(f\"📁 {dataset_name} Dataset\")\n",
+    "    for cls_id, count in counts.items():\n",
+    "        cls_name = CLASS_MAP.get(cls_id, \"UNKNOWN\")\n",
+    "        print(f\"   [{cls_id}] {cls_name:<10}  👉  {count} 개\")\n",
+    "    print(\"\\n\")\n",
+    "\n",
+    "\n",
+    "# ---- Summary 합산 ----\n",
+    "print(\"=============== TOTAL SUMMARY ===============\\n\")\n",
+    "total = defaultdict(int)\n",
+    "\n",
+    "for r in results.values():\n",
+    "    for cls_id, cnt in r.items():\n",
+    "        total[cls_id] += cnt\n",
+    "\n",
+    "for cls_id, cnt in sorted(total.items(), key=lambda x: int(x[0])):\n",
+    "    print(f\"   [{cls_id}] {CLASS_MAP[cls_id]:<10}  👉  {cnt} total\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "62ada642",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "1stagedetect",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

fashion_yolo/aihub_exp/yolov8s_fashion/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8s.pt
+data: /home/cuuva/experiment/fashion_yolo/aihub_fashion.yaml
+epochs: 200
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: aihub_exp
+name: yolov8s_fashion
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fashion_yolo/aihub_exp/yolov8s_fashion

fashion_yolo/aihub_exp/yolov8s_fashion/results.csv

@@ -0,0 +1,27 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,537.591,0.31592,0.73548,0.96999,0.78711,0.7828,0.83314,0.80005,0.2334,0.57004,0.86224,0.0670252,0.000333079,0.000333079
+2,1047.8,0.31123,0.57773,0.96044,0.73462,0.78939,0.8564,0.84804,0.17432,0.50819,0.82295,0.0340219,0.000663114,0.000663114
+3,1562.15,0.29818,0.53937,0.95306,0.84157,0.85019,0.91244,0.90544,0.15707,0.36254,0.81149,0.00101525,0.000989848,0.000989848
+4,2077.15,0.28065,0.49792,0.94603,0.88001,0.87659,0.93355,0.93232,0.11848,0.2798,0.79165,0.00098515,0.00098515,0.00098515
+5,2588.86,0.26853,0.46207,0.94036,0.88174,0.89786,0.94481,0.94383,0.10573,0.24894,0.78506,0.0009802,0.0009802,0.0009802
+6,3099.81,0.25891,0.44161,0.93634,0.9048,0.89586,0.9502,0.94945,0.09195,0.22762,0.78043,0.00097525,0.00097525,0.00097525
+7,3607.6,0.2526,0.42709,0.93365,0.89822,0.91219,0.95607,0.95559,0.08434,0.20666,0.77541,0.0009703,0.0009703,0.0009703
+8,4116.48,0.24902,0.41159,0.93273,0.91249,0.90943,0.95886,0.95852,0.08056,0.19808,0.77446,0.00096535,0.00096535,0.00096535
+9,4631.09,0.24722,0.40261,0.93189,0.90378,0.92017,0.96013,0.95987,0.07751,0.19465,0.77274,0.0009604,0.0009604,0.0009604
+10,5142.15,0.24136,0.39352,0.92883,0.91669,0.91271,0.96146,0.96127,0.07393,0.18613,0.77182,0.00095545,0.00095545,0.00095545
+11,5655.13,0.23686,0.38078,0.92699,0.9137,0.9152,0.96275,0.96259,0.07066,0.1812,0.77011,0.0009505,0.0009505,0.0009505
+12,6166.99,0.23468,0.37665,0.9259,0.91422,0.91415,0.96362,0.96342,0.06915,0.17854,0.76943,0.00094555,0.00094555,0.00094555
+13,6680.34,0.23247,0.36991,0.92494,0.90222,0.9269,0.96386,0.96368,0.0682,0.17739,0.76895,0.0009406,0.0009406,0.0009406
+14,7194.69,0.23053,0.36348,0.92468,0.91431,0.91755,0.96394,0.96378,0.06729,0.17727,0.76854,0.00093565,0.00093565,0.00093565
+15,7707.51,0.22804,0.35867,0.92329,0.91653,0.91783,0.96429,0.96412,0.06656,0.17531,0.76825,0.0009307,0.0009307,0.0009307
+16,8219.29,0.22732,0.35486,0.92281,0.91488,0.91982,0.96437,0.9642,0.06573,0.17464,0.76796,0.00092575,0.00092575,0.00092575
+17,8732.79,0.22742,0.35071,0.92322,0.918,0.91724,0.96453,0.96435,0.06527,0.17411,0.76783,0.0009208,0.0009208,0.0009208
+18,9247.94,0.22677,0.34743,0.92351,0.91517,0.91813,0.96462,0.96443,0.06464,0.17382,0.76765,0.00091585,0.00091585,0.00091585
+19,9762.34,0.22415,0.34395,0.92166,0.9126,0.91959,0.96468,0.9645,0.06444,0.17379,0.76763,0.0009109,0.0009109,0.0009109
+20,10279.6,0.22341,0.33957,0.9218,0.90493,0.92716,0.96487,0.96468,0.06417,0.1738,0.7676,0.00090595,0.00090595,0.00090595
+21,10795.6,0.22162,0.33756,0.92031,0.90863,0.92226,0.96492,0.96477,0.06413,0.17355,0.76753,0.000901,0.000901,0.000901
+22,11311.9,0.22077,0.33169,0.92081,0.90921,0.92403,0.96489,0.96473,0.06397,0.1732,0.7675,0.00089605,0.00089605,0.00089605
+23,11828.2,0.22102,0.33069,0.92076,0.90695,0.92488,0.96507,0.96488,0.06376,0.17277,0.76745,0.0008911,0.0008911,0.0008911
+24,12343.3,inf,0.32755,0.92019,0.90925,0.92283,0.96508,0.96493,0.06385,0.17265,0.76749,0.00088615,0.00088615,0.00088615
+25,12858.3,0.21934,0.32372,0.92008,0.9166,0.91806,0.96515,0.96495,0.06401,0.17222,0.76752,0.0008812,0.0008812,0.0008812
+26,13372.4,0.21782,0.32029,0.91883,0.91643,0.91857,0.96547,0.96526,0.06379,0.17132,0.7674,0.00087625,0.00087625,0.00087625

fashion_yolo/aihub_fashion.yaml

@@ -0,0 +1,7 @@
+train: /home/cuuva/aihub_car/clothes_dataset/Training/images/
+val: /home/cuuva/aihub_car/clothes_dataset/Validation/images/
+# test: /home/cuuva/experiment/datasets/VisDrone/images/test
+
+# nc: 7
+nc: 9
+names: ['BLOUSE','COAT', 'DRESS', 'JACKET', 'JUMPER', 'PANTS', 'SHIRTS', 'SKIRT', 'TSHIRTS']

fashion_yolo/fashion_all.ipynb

@@ -0,0 +1,439 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ed856410",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "📂 폴더 분석: /home/cuuva/experiment/datasets/fashionpedia_yolo/labels/train\n",
+      "📄 파일 개수: 45623\n",
+      "🧮 클래스별 개수:\n",
+      "  class  0 (shirt, blouse): 6161\n",
+      "  class  1 (top, t-shirt, sweatshirt): 16548\n",
+      "  class  2 (sweater): 1494\n",
+      "  class  3 (cardigan): 1107\n",
+      "  class  4 (jacket): 7833\n",
+      "  class  5 (vest): 719\n",
+      "  class  6 (pants): 12414\n",
+      "  class  7 (shorts): 2756\n",
+      "  class  8 (skirt): 5046\n",
+      "  class  9 (coat): 3124\n",
+      "  class 10 (dress): 18739\n",
+      "  class 11 (jumpsuit): 922\n",
+      "  class 12 (cape): 152\n",
+      "  class 13 (glasses): 4855\n",
+      "  class 14 (hat): 2518\n",
+      "  class 15 (hair accessory): 3470\n",
+      "  class 16 (tie): 1457\n",
+      "  class 17 (glove): 1385\n",
+      "  class 18 (watch): 3389\n",
+      "  class 19 (belt): 6851\n",
+      "  class 20 (leg warmer): 112\n",
+      "  class 21 (tights, stockings): 4326\n",
+      "  class 22 (sock): 2582\n",
+      "  class 23 (shoe): 46374\n",
+      "  class 24 (bag, wallet): 7217\n",
+      "  class 25 (scarf): 1374\n",
+      "  class 26 (umbrella): 135\n",
+      "  class 27 (hood): 1226\n",
+      "  class 28 (collar): 10159\n",
+      "  class 29 (lapel): 5972\n",
+      "  class 30 (epaulette): 874\n",
+      "  class 31 (sleeve): 59448\n",
+      "  class 32 (pocket): 27179\n",
+      "  class 33 (neckline): 34258\n",
+      "  class 34 (buckle): 3300\n",
+      "  class 35 (zipper): 7991\n",
+      "  class 36 (applique): 3529\n",
+      "  class 37 (bead): 5084\n",
+      "  class 38 (bow): 528\n",
+      "  class 39 (flower): 1367\n",
+      "  class 40 (fringe): 588\n",
+      "  class 41 (ribbon): 274\n",
+      "  class 42 (rivet): 4893\n",
+      "  class 43 (ruffle): 2407\n",
+      "  class 44 (sequin): 929\n",
+      "  class 45 (tassel): 335\n",
+      "\n",
+      "📂 폴더 분석: /home/cuuva/experiment/datasets/fashionpedia_yolo/labels/val\n",
+      "📄 파일 개수: 1158\n",
+      "🧮 클래스별 개수:\n",
+      "  class  0 (shirt, blouse): 102\n",
+      "  class  1 (top, t-shirt, sweatshirt): 477\n",
+      "  class  2 (sweater): 21\n",
+      "  class  3 (cardigan): 12\n",
+      "  class  4 (jacket): 183\n",
+      "  class  5 (vest): 22\n",
+      "  class  6 (pants): 314\n",
+      "  class  7 (shorts): 106\n",
+      "  class  8 (skirt): 162\n",
+      "  class  9 (coat): 104\n",
+      "  class 10 (dress): 508\n",
+      "  class 11 (jumpsuit): 21\n",
+      "  class 12 (cape): 5\n",
+      "  class 13 (glasses): 130\n",
+      "  class 14 (hat): 74\n",
+      "  class 15 (hair accessory): 109\n",
+      "  class 16 (tie): 3\n",
+      "  class 17 (glove): 31\n",
+      "  class 18 (watch): 84\n",
+      "  class 19 (belt): 164\n",
+      "  class 20 (leg warmer): 14\n",
+      "  class 21 (tights, stockings): 122\n",
+      "  class 22 (sock): 87\n",
+      "  class 23 (shoe): 1566\n",
+      "  class 24 (bag, wallet): 214\n",
+      "  class 25 (scarf): 48\n",
+      "  class 26 (umbrella): 5\n",
+      "  class 27 (hood): 32\n",
+      "  class 28 (collar): 218\n",
+      "  class 29 (lapel): 135\n",
+      "  class 30 (epaulette): 14\n",
+      "  class 31 (sleeve): 1442\n",
+      "  class 32 (pocket): 541\n",
+      "  class 33 (neckline): 929\n",
+      "  class 34 (buckle): 67\n",
+      "  class 35 (zipper): 194\n",
+      "  class 36 (applique): 61\n",
+      "  class 37 (bead): 107\n",
+      "  class 38 (bow): 6\n",
+      "  class 39 (flower): 37\n",
+      "  class 40 (fringe): 30\n",
+      "  class 41 (ribbon): 9\n",
+      "  class 42 (rivet): 143\n",
+      "  class 43 (ruffle): 76\n",
+      "  class 44 (sequin): 13\n",
+      "  class 45 (tassel): 39\n",
+      "\n",
+      "=====================================\n",
+      "📊 전체(train + val) 클래스별 개수\n",
+      "=====================================\n",
+      "  class  0 (shirt, blouse): 6263\n",
+      "  class  1 (top, t-shirt, sweatshirt): 17025\n",
+      "  class  2 (sweater): 1515\n",
+      "  class  3 (cardigan): 1119\n",
+      "  class  4 (jacket): 8016\n",
+      "  class  5 (vest): 741\n",
+      "  class  6 (pants): 12728\n",
+      "  class  7 (shorts): 2862\n",
+      "  class  8 (skirt): 5208\n",
+      "  class  9 (coat): 3228\n",
+      "  class 10 (dress): 19247\n",
+      "  class 11 (jumpsuit): 943\n",
+      "  class 12 (cape): 157\n",
+      "  class 13 (glasses): 4985\n",
+      "  class 14 (hat): 2592\n",
+      "  class 15 (hair accessory): 3579\n",
+      "  class 16 (tie): 1460\n",
+      "  class 17 (glove): 1416\n",
+      "  class 18 (watch): 3473\n",
+      "  class 19 (belt): 7015\n",
+      "  class 20 (leg warmer): 126\n",
+      "  class 21 (tights, stockings): 4448\n",
+      "  class 22 (sock): 2669\n",
+      "  class 23 (shoe): 47940\n",
+      "  class 24 (bag, wallet): 7431\n",
+      "  class 25 (scarf): 1422\n",
+      "  class 26 (umbrella): 140\n",
+      "  class 27 (hood): 1258\n",
+      "  class 28 (collar): 10377\n",
+      "  class 29 (lapel): 6107\n",
+      "  class 30 (epaulette): 888\n",
+      "  class 31 (sleeve): 60890\n",
+      "  class 32 (pocket): 27720\n",
+      "  class 33 (neckline): 35187\n",
+      "  class 34 (buckle): 3367\n",
+      "  class 35 (zipper): 8185\n",
+      "  class 36 (applique): 3590\n",
+      "  class 37 (bead): 5191\n",
+      "  class 38 (bow): 534\n",
+      "  class 39 (flower): 1404\n",
+      "  class 40 (fringe): 618\n",
+      "  class 41 (ribbon): 283\n",
+      "  class 42 (rivet): 5036\n",
+      "  class 43 (ruffle): 2483\n",
+      "  class 44 (sequin): 942\n",
+      "  class 45 (tassel): 374\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from collections import defaultdict\n",
+    "import yaml\n",
+    "\n",
+    "# ---------------------------------------\n",
+    "# 1) YAML 파일에서 클래스 이름 불러오기\n",
+    "# ---------------------------------------\n",
+    "yaml_path = \"/home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_bak.yaml\"\n",
+    "\n",
+    "with open(yaml_path, \"r\") as f:\n",
+    "    data = yaml.safe_load(f)\n",
+    "\n",
+    "names = data[\"names\"]\n",
+    "# keys가 문자열일 수도 있음 → 정수 key로 맞춰줌\n",
+    "class_names = {int(k): v for k, v in names.items()}\n",
+    "\n",
+    "# ---------------------------------------\n",
+    "# 2) Label 파일 읽어서 클래스별 개수 계산\n",
+    "# ---------------------------------------\n",
+    "label_root = \"/home/cuuva/experiment/datasets/fashionpedia_yolo/labels\"\n",
+    "folders = [\"train\", \"val\"]\n",
+    "\n",
+    "total_counts = defaultdict(int)\n",
+    "\n",
+    "for folder in folders:\n",
+    "    folder_path = os.path.join(label_root, folder)\n",
+    "    class_counts = defaultdict(int)\n",
+    "\n",
+    "    txt_files = [f for f in os.listdir(folder_path) if f.endswith(\".txt\")]\n",
+    "\n",
+    "    print(f\"\\n📂 폴더 분석: {folder_path}\")\n",
+    "    print(f\"📄 파일 개수: {len(txt_files)}\")\n",
+    "\n",
+    "    for txt in txt_files:\n",
+    "        with open(os.path.join(folder_path, txt), \"r\") as f:\n",
+    "            lines = f.readlines()\n",
+    "\n",
+    "        for line in lines:\n",
+    "            class_id = int(line.split()[0])\n",
+    "            class_counts[class_id] += 1\n",
+    "            total_counts[class_id] += 1\n",
+    "\n",
+    "    # --- 폴더별 결과 출력 ---\n",
+    "    print(\"🧮 클래스별 개수:\")\n",
+    "    for cid in sorted(class_counts.keys()):\n",
+    "        print(f\"  class {cid:2d} ({class_names.get(cid, 'Unknown')}): {class_counts[cid]}\")\n",
+    "\n",
+    "# ---------------------------------------\n",
+    "# 3) 전체 합산 결과 출력\n",
+    "# ---------------------------------------\n",
+    "print(\"\\n=====================================\")\n",
+    "print(\"📊 전체(train + val) 클래스별 개수\")\n",
+    "print(\"=====================================\")\n",
+    "for cid in sorted(total_counts.keys()):\n",
+    "    print(f\"  class {cid:2d} ({class_names.get(cid, 'Unknown')}): {total_counts[cid]}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "d94803f3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "New https://pypi.org/project/ultralytics/8.3.237 available 😃 Update with 'pip install -U ultralytics'\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32109MiB)\n",
+      "\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, augment=False, auto_augment=randaugment, batch=-1, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=/home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_bak.yaml, degrees=0.0, deterministic=True, device=0, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, epochs=500, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.001, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolov8m.pt, momentum=0.937, mosaic=1.0, multi_scale=False, name=yolov8m_fashion_all, nbs=64, nms=False, opset=None, optimize=False, optimizer=AdamW, overlap_mask=True, patience=50, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=fashionpedia_exp, rect=False, resume=False, retina_masks=False, save=True, save_conf=False, save_crop=False, save_dir=/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n",
+      "Overriding model.yaml nc=80 with nc=46\n",
+      "\n",
+      "                   from  n    params  module                                       arguments                     \n",
+      "  0                  -1  1      1392  ultralytics.nn.modules.conv.Conv             [3, 48, 3, 2]                 \n",
+      "  1                  -1  1     41664  ultralytics.nn.modules.conv.Conv             [48, 96, 3, 2]                \n",
+      "  2                  -1  2    111360  ultralytics.nn.modules.block.C2f             [96, 96, 2, True]             \n",
+      "  3                  -1  1    166272  ultralytics.nn.modules.conv.Conv             [96, 192, 3, 2]               \n",
+      "  4                  -1  4    813312  ultralytics.nn.modules.block.C2f             [192, 192, 4, True]           \n",
+      "  5                  -1  1    664320  ultralytics.nn.modules.conv.Conv             [192, 384, 3, 2]              \n",
+      "  6                  -1  4   3248640  ultralytics.nn.modules.block.C2f             [384, 384, 4, True]           \n",
+      "  7                  -1  1   1991808  ultralytics.nn.modules.conv.Conv             [384, 576, 3, 2]              \n",
+      "  8                  -1  2   3985920  ultralytics.nn.modules.block.C2f             [576, 576, 2, True]           \n",
+      "  9                  -1  1    831168  ultralytics.nn.modules.block.SPPF            [576, 576, 5]                 \n",
+      " 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 12                  -1  2   1993728  ultralytics.nn.modules.block.C2f             [960, 384, 2]                 \n",
+      " 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 15                  -1  2    517632  ultralytics.nn.modules.block.C2f             [576, 192, 2]                 \n",
+      " 16                  -1  1    332160  ultralytics.nn.modules.conv.Conv             [192, 192, 3, 2]              \n",
+      " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 18                  -1  2   1846272  ultralytics.nn.modules.block.C2f             [576, 384, 2]                 \n",
+      " 19                  -1  1   1327872  ultralytics.nn.modules.conv.Conv             [384, 384, 3, 2]              \n",
+      " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 21                  -1  2   4207104  ultralytics.nn.modules.block.C2f             [960, 576, 2]                 \n",
+      " 22        [15, 18, 21]  1   3802330  ultralytics.nn.modules.head.Detect           [46, [192, 384, 576]]         \n",
+      "Model summary: 169 layers, 25,882,954 parameters, 25,882,938 gradients, 79.2 GFLOPs\n",
+      "\n",
+      "Transferred 469/475 items from pretrained weights\n",
+      "Freezing layer 'model.22.dfl.conv.weight'\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 3322.6±3977.1 MB/s, size: 88.2 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/experiment/datasets/fashionpedia_yolo/labels/train... 45623 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 45623/45623 7.9Kit/s 5.8s0.0s\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/fashionpedia_yolo/images/train/19725.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /home/cuuva/experiment/datasets/fashionpedia_yolo/labels/train.cache\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mComputing optimal batch size for imgsz=640 at 60.0% CUDA memory utilization.\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mCUDA:0 (NVIDIA GeForce RTX 5090) 31.36G total, 0.25G reserved, 0.24G allocated, 30.87G free\n",
+      "      Params      GFLOPs  GPU_mem (GB)  forward (ms) backward (ms)                   input                  output\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/cuuva/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "    25882954       79.21         2.898         28.43         155.4        (1, 3, 640, 640)                    list\n",
+      "    25882954       158.4         4.754         9.878         36.17        (2, 3, 640, 640)                    list\n",
+      "    25882954       316.8         5.887          13.6            50        (4, 3, 640, 640)                    list\n",
+      "    25882954       633.7         8.972         26.37         74.09        (8, 3, 640, 640)                    list\n",
+      "    25882954        1267        12.149         27.28         121.9       (16, 3, 640, 640)                    list\n",
+      "    25882954        2535        20.816         55.09         243.1       (32, 3, 640, 640)                    list\n",
+      "    25882954        5069        20.615         117.7         484.3       (64, 3, 640, 640)                    list\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mUsing batch-size 28 for CUDA:0 19.32G/31.36G (62%) ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 5333.7±2302.8 MB/s, size: 66.6 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/experiment/datasets/fashionpedia_yolo/labels/train.cache... 45623 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 45623/45623 90.6Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/fashionpedia_yolo/images/train/19725.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 3235.1±1428.7 MB/s, size: 71.1 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /home/cuuva/experiment/datasets/fashionpedia_yolo/labels/val... 1158 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 1158/1158 6.4Kit/s 0.2s4s\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /home/cuuva/experiment/datasets/fashionpedia_yolo/labels/val.cache\n",
+      "Plotting labels to /home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/labels.jpg... \n",
+      "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.001, momentum=0.937) with parameter groups 77 weight(decay=0.0), 84 weight(decay=0.0004375), 83 bias(decay=0.0)\n",
+      "Image sizes 640 train, 640 val\n",
+      "Using 8 dataloader workers\n",
+      "Logging results to \u001b[1m/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all\u001b[0m\n",
+      "Starting training for 500 epochs...\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      1/500      12.3G      1.118      1.526      1.247        379        640: 76% ━━━━━━━━━─── 1232/1630 8.0it/s 5:18<49.7s\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[2], line 8\u001b[0m\n\u001b[1;32m      4\u001b[0m model \u001b[38;5;241m=\u001b[39m YOLO(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124myolov8m.pt\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m      6\u001b[0m \u001b[38;5;66;03m# 2. 학습 실행\u001b[39;00m\n\u001b[1;32m      7\u001b[0m \u001b[38;5;66;03m# 위에서 생성된 yaml 파일 경로를 넣어줍니다.\u001b[39;00m\n\u001b[0;32m----> 8\u001b[0m train_results \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      9\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_bak.yaml\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m     10\u001b[0m \u001b[43m    \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m500\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m            \u001b[49m\n\u001b[1;32m     11\u001b[0m \u001b[43m    \u001b[49m\u001b[43mimgsz\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m640\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     12\u001b[0m \u001b[43m    \u001b[49m\u001b[43mbatch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m              \u001b[49m\n\u001b[1;32m     13\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdevice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcuda\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptimizer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mAdamW\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     15\u001b[0m \u001b[43m    \u001b[49m\u001b[43mlr0\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.001\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     16\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpatience\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m50\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     17\u001b[0m \u001b[43m    \u001b[49m\u001b[43mproject\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mfashionpedia_exp\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     18\u001b[0m \u001b[43m    \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43myolov8m_fashion_all\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     19\u001b[0m \u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/engine/model.py:777\u001b[0m, in \u001b[0;36mModel.train\u001b[0;34m(self, trainer, **kwargs)\u001b[0m\n\u001b[1;32m    774\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer\u001b[38;5;241m.\u001b[39mget_model(weights\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mckpt \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m, cfg\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\u001b[38;5;241m.\u001b[39myaml)\n\u001b[1;32m    775\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer\u001b[38;5;241m.\u001b[39mmodel\n\u001b[0;32m--> 777\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    778\u001b[0m \u001b[38;5;66;03m# Update model and cfg after training\u001b[39;00m\n\u001b[1;32m    779\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m RANK \u001b[38;5;129;01min\u001b[39;00m {\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m0\u001b[39m}:\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/engine/trainer.py:238\u001b[0m, in \u001b[0;36mBaseTrainer.train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    235\u001b[0m         ddp_cleanup(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28mstr\u001b[39m(file))\n\u001b[1;32m    237\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 238\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_do_train\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/engine/trainer.py:422\u001b[0m, in \u001b[0;36mBaseTrainer._do_train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    420\u001b[0m     loss, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloss_items \u001b[38;5;241m=\u001b[39m unwrap_model(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel)\u001b[38;5;241m.\u001b[39mloss(batch, preds)\n\u001b[1;32m    421\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 422\u001b[0m     loss, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloss_items \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    423\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloss \u001b[38;5;241m=\u001b[39m loss\u001b[38;5;241m.\u001b[39msum()\n\u001b[1;32m    424\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m RANK \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m:\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/torch/nn/modules/module.py:1775\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1773\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1774\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1775\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/torch/nn/modules/module.py:1786\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1781\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1782\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1783\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1784\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1785\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1786\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1788\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1789\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/nn/tasks.py:136\u001b[0m, in \u001b[0;36mBaseModel.forward\u001b[0;34m(self, x, *args, **kwargs)\u001b[0m\n\u001b[1;32m    123\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Perform forward pass of the model for either training or inference.\u001b[39;00m\n\u001b[1;32m    124\u001b[0m \n\u001b[1;32m    125\u001b[0m \u001b[38;5;124;03mIf x is a dict, calculates and returns the loss for training. Otherwise, returns predictions for inference.\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    133\u001b[0m \u001b[38;5;124;03m    (torch.Tensor): Loss if x is a dict (training), or network predictions (inference).\u001b[39;00m\n\u001b[1;32m    134\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    135\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mdict\u001b[39m):  \u001b[38;5;66;03m# for cases of training and validating while training.\u001b[39;00m\n\u001b[0;32m--> 136\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloss\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    137\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpredict(x, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/nn/tasks.py:328\u001b[0m, in \u001b[0;36mBaseModel.loss\u001b[0;34m(self, batch, preds)\u001b[0m\n\u001b[1;32m    326\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m preds \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    327\u001b[0m     preds \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mforward(batch[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mimg\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[0;32m--> 328\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcriterion\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpreds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/utils/loss.py:270\u001b[0m, in \u001b[0;36mv8DetectionLoss.__call__\u001b[0;34m(self, preds, batch)\u001b[0m\n\u001b[1;32m    266\u001b[0m pred_bboxes \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbbox_decode(anchor_points, pred_distri)  \u001b[38;5;66;03m# xyxy, (b, h*w, 4)\u001b[39;00m\n\u001b[1;32m    267\u001b[0m \u001b[38;5;66;03m# dfl_conf = pred_distri.view(batch_size, -1, 4, self.reg_max).detach().softmax(-1)\u001b[39;00m\n\u001b[1;32m    268\u001b[0m \u001b[38;5;66;03m# dfl_conf = (dfl_conf.amax(-1).mean(-1) + dfl_conf.amax(-1).amin(-1)) / 2\u001b[39;00m\n\u001b[0;32m--> 270\u001b[0m _, target_bboxes, target_scores, fg_mask, _ \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43massigner\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    271\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# pred_scores.detach().sigmoid() * 0.8 + dfl_conf.unsqueeze(-1) * 0.2,\u001b[39;49;00m\n\u001b[1;32m    272\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpred_scores\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdetach\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msigmoid\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    273\u001b[0m \u001b[43m    \u001b[49m\u001b[43m(\u001b[49m\u001b[43mpred_bboxes\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdetach\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mstride_tensor\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtype\u001b[49m\u001b[43m(\u001b[49m\u001b[43mgt_bboxes\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    274\u001b[0m \u001b[43m    \u001b[49m\u001b[43manchor_points\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mstride_tensor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    275\u001b[0m \u001b[43m    \u001b[49m\u001b[43mgt_labels\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    276\u001b[0m \u001b[43m    \u001b[49m\u001b[43mgt_bboxes\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    277\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmask_gt\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    278\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    280\u001b[0m target_scores_sum \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mmax\u001b[39m(target_scores\u001b[38;5;241m.\u001b[39msum(), \u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m    282\u001b[0m \u001b[38;5;66;03m# Cls loss\u001b[39;00m\n\u001b[1;32m    283\u001b[0m \u001b[38;5;66;03m# loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way\u001b[39;00m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/torch/nn/modules/module.py:1775\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1773\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1774\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1775\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/torch/nn/modules/module.py:1786\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1781\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1782\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1783\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1784\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1785\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1786\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1788\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1789\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/torch/utils/_contextlib.py:120\u001b[0m, in \u001b[0;36mcontext_decorator.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    117\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m    118\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m    119\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 120\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/utils/tal.py:79\u001b[0m, in \u001b[0;36mTaskAlignedAssigner.forward\u001b[0;34m(self, pd_scores, pd_bboxes, anc_points, gt_labels, gt_bboxes, mask_gt)\u001b[0m\n\u001b[1;32m     70\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[1;32m     71\u001b[0m         torch\u001b[38;5;241m.\u001b[39mfull_like(pd_scores[\u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m, \u001b[38;5;241m0\u001b[39m], \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnum_classes),\n\u001b[1;32m     72\u001b[0m         torch\u001b[38;5;241m.\u001b[39mzeros_like(pd_bboxes),\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     75\u001b[0m         torch\u001b[38;5;241m.\u001b[39mzeros_like(pd_scores[\u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m, \u001b[38;5;241m0\u001b[39m]),\n\u001b[1;32m     76\u001b[0m     )\n\u001b[1;32m     78\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 79\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpd_scores\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpd_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43manc_points\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgt_labels\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgt_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmask_gt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     80\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mOutOfMemoryError:\n\u001b[1;32m     81\u001b[0m     \u001b[38;5;66;03m# Move tensors to CPU, compute, then move back to original device\u001b[39;00m\n\u001b[1;32m     82\u001b[0m     LOGGER\u001b[38;5;241m.\u001b[39mwarning(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCUDA OutOfMemoryError in TaskAlignedAssigner, using CPU\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/utils/tal.py:105\u001b[0m, in \u001b[0;36mTaskAlignedAssigner._forward\u001b[0;34m(self, pd_scores, pd_bboxes, anc_points, gt_labels, gt_bboxes, mask_gt)\u001b[0m\n\u001b[1;32m     87\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21m_forward\u001b[39m(\u001b[38;5;28mself\u001b[39m, pd_scores, pd_bboxes, anc_points, gt_labels, gt_bboxes, mask_gt):\n\u001b[1;32m     88\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Compute the task-aligned assignment.\u001b[39;00m\n\u001b[1;32m     89\u001b[0m \n\u001b[1;32m     90\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    103\u001b[0m \u001b[38;5;124;03m        target_gt_idx (torch.Tensor): Target ground truth indices with shape (bs, num_total_anchors).\u001b[39;00m\n\u001b[1;32m    104\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 105\u001b[0m     mask_pos, align_metric, overlaps \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_pos_mask\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    106\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpd_scores\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpd_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgt_labels\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgt_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43manc_points\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmask_gt\u001b[49m\n\u001b[1;32m    107\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    109\u001b[0m     target_gt_idx, fg_mask, mask_pos \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mselect_highest_overlaps(mask_pos, overlaps, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_max_boxes)\n\u001b[1;32m    111\u001b[0m     \u001b[38;5;66;03m# Assigned target\u001b[39;00m\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/utils/tal.py:141\u001b[0m, in \u001b[0;36mTaskAlignedAssigner.get_pos_mask\u001b[0;34m(self, pd_scores, pd_bboxes, gt_labels, gt_bboxes, anc_points, mask_gt)\u001b[0m\n\u001b[1;32m    139\u001b[0m mask_in_gts \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mselect_candidates_in_gts(anc_points, gt_bboxes)\n\u001b[1;32m    140\u001b[0m \u001b[38;5;66;03m# Get anchor_align metric, (b, max_num_obj, h*w)\u001b[39;00m\n\u001b[0;32m--> 141\u001b[0m align_metric, overlaps \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_box_metrics\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpd_scores\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpd_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgt_labels\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgt_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmask_in_gts\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mmask_gt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    142\u001b[0m \u001b[38;5;66;03m# Get topk_metric mask, (b, max_num_obj, h*w)\u001b[39;00m\n\u001b[1;32m    143\u001b[0m mask_topk \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mselect_topk_candidates(align_metric, topk_mask\u001b[38;5;241m=\u001b[39mmask_gt\u001b[38;5;241m.\u001b[39mexpand(\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtopk)\u001b[38;5;241m.\u001b[39mbool())\n",
+      "File \u001b[0;32m~/anaconda3/envs/1stagedetect/lib/python3.10/site-packages/ultralytics/utils/tal.py:175\u001b[0m, in \u001b[0;36mTaskAlignedAssigner.get_box_metrics\u001b[0;34m(self, pd_scores, pd_bboxes, gt_labels, gt_bboxes, mask_gt)\u001b[0m\n\u001b[1;32m    172\u001b[0m bbox_scores[mask_gt] \u001b[38;5;241m=\u001b[39m pd_scores[ind[\u001b[38;5;241m0\u001b[39m], :, ind[\u001b[38;5;241m1\u001b[39m]][mask_gt]  \u001b[38;5;66;03m# b, max_num_obj, h*w\u001b[39;00m\n\u001b[1;32m    174\u001b[0m \u001b[38;5;66;03m# (b, max_num_obj, 1, 4), (b, 1, h*w, 4)\u001b[39;00m\n\u001b[0;32m--> 175\u001b[0m pd_boxes \u001b[38;5;241m=\u001b[39m \u001b[43mpd_bboxes\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43munsqueeze\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mexpand(\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_max_boxes, \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)[mask_gt]\n\u001b[1;32m    176\u001b[0m gt_boxes \u001b[38;5;241m=\u001b[39m gt_bboxes\u001b[38;5;241m.\u001b[39munsqueeze(\u001b[38;5;241m2\u001b[39m)\u001b[38;5;241m.\u001b[39mexpand(\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, na, \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)[mask_gt]\n\u001b[1;32m    177\u001b[0m overlaps[mask_gt] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miou_calculation(gt_boxes, pd_boxes)\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "from ultralytics import YOLO\n",
+    "\n",
+    "# 1. 모델 로드 (YOLOv8m 사용)\n",
+    "model = YOLO('yolov8m.pt')\n",
+    "\n",
+    "# 2. 학습 실행\n",
+    "# 위에서 생성된 yaml 파일 경로를 넣어줍니다.\n",
+    "train_results = model.train(\n",
+    "    data=\"/home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_bak.yaml\", \n",
+    "    epochs=500,            \n",
+    "    imgsz=640,\n",
+    "    batch=-1,              \n",
+    "    device=\"cuda\",\n",
+    "    optimizer='AdamW',\n",
+    "    lr0=0.001,\n",
+    "    patience=50,\n",
+    "    project='fashionpedia_exp',\n",
+    "    name='yolov8m_fashion_all',\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9de5e25b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32109MiB)\n",
+      "Model summary (fused): 92 layers, 25,866,394 parameters, 0 gradients, 78.8 GFLOPs\n",
+      "\n",
+      "\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from '/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/weights/best_fashion_detect_all.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 50, 8400) (49.7 MB)\n",
+      "\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m starting export with onnx 1.19.1 opset 20...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m slimming with onnxslim 0.1.71...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m export success ✅ 0.9s, saved as '/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/weights/best_fashion_detect_all.onnx' (98.9 MB)\n",
+      "\n",
+      "Export complete (1.4s)\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/weights\u001b[0m\n",
+      "Predict:         yolo predict task=detect model=/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/weights/best_fashion_detect_all.onnx imgsz=640  \n",
+      "Validate:        yolo val task=detect model=/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/weights/best_fashion_detect_all.onnx imgsz=640 data=/home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_bak.yaml  \n",
+      "Visualize:       https://netron.app\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/weights/best_fashion_detect_all.onnx'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from ultralytics import YOLO\n",
+    "model = YOLO(\"/home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/weights/best_fashion_detect_all.pt\")\n",
+    "model.export(format=\"onnx\", imgsz=640, device=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a77ad845",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "1stagedetect",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

fashion_yolo/fashionpedia_exp/yolov8m_fashion+face/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_custom.yaml
+epochs: 500
+time: null
+patience: 100
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fashionpedia_exp
+name: yolov8m_fashion+face
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion+face

fashion_yolo/fashionpedia_exp/yolov8m_fashion+face/results.csv

@@ -0,0 +1,149 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,467.057,0.81693,1.12746,1.11612,0.54533,0.39001,0.3928,0.29481,0.83096,0.9068,1.04598,0.0670304,0.000333027,0.000333027
+2,935.528,0.80969,1.01999,1.11239,0.58249,0.4265,0.45098,0.34294,0.79094,0.83315,1.02486,0.034029,0.000665041,0.000665041
+3,1403.24,0.77545,0.95443,1.0934,0.60362,0.48918,0.53296,0.42692,0.66897,0.69128,0.96869,0.0010264,0.000995735,0.000995735
+4,1867.28,0.69526,0.84232,1.04912,0.55647,0.57369,0.5656,0.45762,0.63462,0.631,0.95357,0.00099406,0.00099406,0.00099406
+5,2331.34,0.66974,0.8034,1.03568,0.67283,0.517,0.58531,0.48487,0.60306,0.59998,0.94113,0.00099208,0.00099208,0.00099208
+6,2795.27,0.65377,0.77574,1.02698,0.61599,0.58064,0.60414,0.49684,0.58512,0.58784,0.93346,0.0009901,0.0009901,0.0009901
+7,3258.75,0.63937,0.75073,1.01797,0.62045,0.58785,0.62562,0.51724,0.5769,0.56478,0.93021,0.00098812,0.00098812,0.00098812
+8,3722.58,0.62693,0.73014,1.01106,0.69556,0.61687,0.66601,0.55158,0.56688,0.53685,0.92476,0.00098614,0.00098614,0.00098614
+9,4186.46,0.61949,0.7154,1.00696,0.67596,0.62899,0.66082,0.55676,0.5523,0.53072,0.91756,0.00098416,0.00098416,0.00098416
+10,4650.19,0.60957,0.70193,1.00275,0.73885,0.62388,0.67504,0.56706,0.54429,0.51469,0.91708,0.00098218,0.00098218,0.00098218
+11,5114.28,0.60425,0.68863,0.99893,0.69136,0.64269,0.67954,0.5778,0.53208,0.50031,0.90859,0.0009802,0.0009802,0.0009802
+12,5578.44,0.59478,0.67847,0.99458,0.7075,0.63317,0.69369,0.59201,0.52279,0.49295,0.904,0.00097822,0.00097822,0.00097822
+13,6042.37,0.5887,0.66591,0.9908,0.76371,0.62884,0.70385,0.60097,0.51638,0.48391,0.90036,0.00097624,0.00097624,0.00097624
+14,6512.06,0.58261,0.65644,0.98777,0.74316,0.652,0.71859,0.61435,0.5078,0.47993,0.89855,0.00097426,0.00097426,0.00097426
+15,6976.05,0.57974,0.64695,0.9851,0.75534,0.65491,0.72066,0.61845,0.50818,0.47139,0.89856,0.00097228,0.00097228,0.00097228
+16,7440.32,0.57205,0.6371,0.98256,0.7202,0.68237,0.7228,0.62345,0.50565,0.46069,0.89822,0.0009703,0.0009703,0.0009703
+17,7904.66,0.56831,0.62784,0.98011,0.74443,0.67453,0.72164,0.62184,0.49883,0.45869,0.89593,0.00096832,0.00096832,0.00096832
+18,8368.77,0.564,0.62095,0.97782,0.78102,0.66905,0.73814,0.6364,0.49399,0.45245,0.89525,0.00096634,0.00096634,0.00096634
+19,8833.21,0.56125,0.61312,0.97591,0.78344,0.67802,0.74498,0.64284,0.49224,0.45233,0.89184,0.00096436,0.00096436,0.00096436
+20,9291.53,0.55746,0.60413,0.97227,0.74325,0.69505,0.74347,0.6409,0.48917,0.44875,0.89043,0.00096238,0.00096238,0.00096238
+21,9749.03,0.55175,0.59783,0.97195,0.71419,0.7172,0.7511,0.65253,0.48452,0.44122,0.88902,0.0009604,0.0009604,0.0009604
+22,10206.1,0.54774,0.59105,0.97042,0.75634,0.70744,0.76003,0.66179,0.48349,0.43958,0.88969,0.00095842,0.00095842,0.00095842
+23,10663.1,0.54698,0.58527,0.96958,0.79148,0.70269,0.76288,0.66043,0.47955,0.43799,0.88831,0.00095644,0.00095644,0.00095644
+24,11120.1,0.54339,0.57915,0.96632,0.7589,0.72312,0.75601,0.65612,0.47758,0.43662,0.88685,0.00095446,0.00095446,0.00095446
+25,11576.9,0.53908,0.57337,0.966,0.75346,0.72104,0.75521,0.65778,0.47665,0.43568,0.88706,0.00095248,0.00095248,0.00095248
+26,12034.2,0.53659,0.56695,0.96264,0.76518,0.71979,0.75664,0.66037,0.47398,0.43574,0.88628,0.0009505,0.0009505,0.0009505
+27,12491.6,0.53434,0.5621,0.9611,0.75036,0.72955,0.75745,0.66184,0.47184,0.4337,0.88512,0.00094852,0.00094852,0.00094852
+28,12948.7,0.53181,0.55533,0.95866,0.76131,0.71555,0.76207,0.66557,0.47057,0.43263,0.88423,0.00094654,0.00094654,0.00094654
+29,13406,0.52823,0.55253,0.95889,0.7727,0.71127,0.76412,0.66749,0.46989,0.43108,0.8842,0.00094456,0.00094456,0.00094456
+30,13863.4,0.52584,0.54711,0.95825,0.78324,0.70842,0.76374,0.66892,0.46828,0.43001,0.88362,0.00094258,0.00094258,0.00094258
+31,14321.1,0.52382,0.54327,0.95609,0.79574,0.70657,0.76396,0.66882,0.46715,0.42887,0.88314,0.0009406,0.0009406,0.0009406
+32,14778.2,0.52337,0.53802,0.95528,0.7811,0.71463,0.76726,0.67271,0.46727,0.42801,0.88386,0.00093862,0.00093862,0.00093862
+33,15235.6,0.51967,0.5331,0.95356,0.78128,0.71613,0.76771,0.67353,0.46689,0.42677,0.88364,0.00093664,0.00093664,0.00093664
+34,15692.4,0.52036,0.53114,0.95386,0.77695,0.71925,0.77107,0.6759,0.46628,0.42561,0.88331,0.00093466,0.00093466,0.00093466
+35,16149.8,0.51783,0.52731,0.95243,0.7758,0.72485,0.77273,0.6774,0.46583,0.42431,0.8835,0.00093268,0.00093268,0.00093268
+36,16607.1,0.51416,0.52285,0.95134,0.7807,0.72425,0.77242,0.67756,0.46569,0.42426,0.88394,0.0009307,0.0009307,0.0009307
+37,17064.7,0.51309,0.51764,0.94941,0.78396,0.71824,0.77182,0.67722,0.46545,0.42395,0.88402,0.00092872,0.00092872,0.00092872
+38,17521.7,0.51026,0.51577,0.95043,0.78847,0.71526,0.77277,0.6786,0.46515,0.42321,0.88431,0.00092674,0.00092674,0.00092674
+39,17978.9,0.50843,0.50893,0.94436,0.78724,0.71607,0.77334,0.67763,0.46416,0.42294,0.88322,0.00092476,0.00092476,0.00092476
+40,18436,0.50889,0.50743,0.94803,0.78949,0.71617,0.77456,0.67961,0.46341,0.42322,0.88274,0.00092278,0.00092278,0.00092278
+41,18893.8,0.50464,0.5022,0.94493,0.78714,0.72178,0.77634,0.68105,0.46338,0.42328,0.88275,0.0009208,0.0009208,0.0009208
+42,19351.1,0.50424,0.49693,0.94267,0.78618,0.7212,0.77657,0.68135,0.46306,0.4243,0.88246,0.00091882,0.00091882,0.00091882
+43,19808.8,0.50157,0.49782,0.9415,0.78257,0.72396,0.77632,0.68339,0.46261,0.42337,0.88195,0.00091684,0.00091684,0.00091684
+44,20265.3,0.50046,0.49344,0.94201,0.78197,0.72435,0.77725,0.68406,0.46146,0.42295,0.88097,0.00091486,0.00091486,0.00091486
+45,20722.9,0.50013,0.4901,0.94178,0.77366,0.72358,0.77725,0.68436,0.46148,0.42276,0.88064,0.00091288,0.00091288,0.00091288
+46,21179.9,0.49718,0.48691,0.93874,0.77525,0.72767,0.77668,0.68472,0.46082,0.42207,0.8803,0.0009109,0.0009109,0.0009109
+47,21637.4,0.49619,0.48468,0.94083,0.77476,0.72626,0.77704,0.68558,0.46006,0.42076,0.87981,0.00090892,0.00090892,0.00090892
+48,22094.2,0.496,0.48359,0.94045,0.77279,0.72727,0.77778,0.68623,0.45911,0.41981,0.87924,0.00090694,0.00090694,0.00090694
+49,22551.1,0.49226,0.47864,0.93811,0.77877,0.7243,0.77754,0.68554,0.45885,0.4194,0.87887,0.00090496,0.00090496,0.00090496
+50,23008,0.49142,0.47693,0.93952,0.78685,0.72566,0.77839,0.68674,0.45826,0.41808,0.87876,0.00090298,0.00090298,0.00090298
+51,23465.2,0.49063,0.47228,0.93746,0.78727,0.71737,0.77756,0.68611,0.45794,0.41835,0.8789,0.000901,0.000901,0.000901
+52,23922.4,0.49277,0.47346,0.93698,0.79896,0.71359,0.77682,0.68592,0.45764,0.41908,0.87888,0.00089902,0.00089902,0.00089902
+53,24379.3,0.48874,0.4681,0.93659,0.80174,0.7089,0.77739,0.68646,0.45716,0.41974,0.87853,0.00089704,0.00089704,0.00089704
+54,24836.1,0.48684,0.46737,0.93502,0.80014,0.71472,0.7776,0.68744,0.45694,0.41981,0.87846,0.00089506,0.00089506,0.00089506
+55,25293,0.48609,0.46297,0.93441,0.80951,0.70669,0.7783,0.68803,0.45686,0.41992,0.87849,0.00089308,0.00089308,0.00089308
+56,25749.6,0.48778,0.46382,0.9338,0.82277,0.70775,0.77801,0.68791,0.45693,0.42021,0.87861,0.0008911,0.0008911,0.0008911
+57,26207.1,0.48345,0.4615,0.9339,0.81973,0.70701,0.77692,0.68636,0.45705,0.421,0.8786,0.00088912,0.00088912,0.00088912
+58,26663.7,0.48171,0.45549,0.93135,0.78953,0.70906,0.7758,0.68529,0.45698,0.42079,0.87847,0.00088714,0.00088714,0.00088714
+59,27120.8,0.4829,0.45529,0.93213,0.79176,0.70614,0.7739,0.68357,0.4568,0.42125,0.87816,0.00088516,0.00088516,0.00088516
+60,27577.2,0.48051,0.45312,0.93211,0.80325,0.70479,0.77414,0.68308,0.45658,0.42082,0.87806,0.00088318,0.00088318,0.00088318
+61,28034,0.47899,0.45065,0.93165,0.79931,0.70471,0.77423,0.68257,0.45691,0.4208,0.87855,0.0008812,0.0008812,0.0008812
+62,28491,0.47958,0.44895,0.93011,0.79137,0.70373,0.7737,0.68239,0.45634,0.42075,0.87815,0.00087922,0.00087922,0.00087922
+63,28948.1,0.4767,0.44567,0.93035,0.79866,0.69783,0.77472,0.68291,0.45611,0.42045,0.87829,0.00087724,0.00087724,0.00087724
+64,29405.3,0.47688,0.44559,0.9299,0.77824,0.70628,0.77419,0.68323,0.45611,0.42006,0.87866,0.00087526,0.00087526,0.00087526
+65,29862.4,0.47644,0.4422,0.92813,0.76677,0.7267,0.77378,0.68248,0.45633,0.42018,0.8792,0.00087328,0.00087328,0.00087328
+66,30319.4,0.47647,0.44285,0.92968,0.7673,0.72557,0.77459,0.68248,0.45623,0.42038,0.87927,0.0008713,0.0008713,0.0008713
+67,30776.4,0.47252,0.43681,0.92775,0.76907,0.7251,0.77551,0.68324,0.45608,0.42079,0.87911,0.00086932,0.00086932,0.00086932
+68,31233.3,0.4711,0.43378,0.92607,0.76942,0.72093,0.77494,0.6832,0.45554,0.42074,0.87866,0.00086734,0.00086734,0.00086734
+69,31690.7,0.47249,0.43583,0.92663,0.7645,0.73173,0.77535,0.68276,0.45504,0.42129,0.87827,0.00086536,0.00086536,0.00086536
+70,32147.6,0.46949,0.43015,0.92474,0.75754,0.73054,0.77827,0.68592,0.45442,0.42064,0.8779,0.00086338,0.00086338,0.00086338
+71,32604.7,0.46907,0.42979,0.92388,0.74692,0.7441,0.77871,0.68564,0.45433,0.42132,0.87786,0.0008614,0.0008614,0.0008614
+72,33061.5,0.46846,0.42863,0.92253,0.73621,0.75454,0.77869,0.68633,0.45423,0.42121,0.87761,0.00085942,0.00085942,0.00085942
+73,33518.5,0.46762,0.42615,0.92471,0.73202,0.75631,0.77545,0.68323,0.45405,0.42108,0.87764,0.00085744,0.00085744,0.00085744
+74,33975.5,0.46791,0.42613,0.9243,0.73907,0.75753,0.77318,0.68249,0.45351,0.42158,0.87765,0.00085546,0.00085546,0.00085546
+75,34432.5,0.46608,0.42433,0.92408,0.73007,0.76396,0.7725,0.68094,0.45398,0.42129,0.8783,0.00085348,0.00085348,0.00085348
+76,34889.9,0.46584,0.4229,0.92379,0.73199,0.76402,0.77224,0.68086,0.45426,0.42198,0.87884,0.0008515,0.0008515,0.0008515
+77,35347.3,0.46535,0.42133,0.92254,0.81113,0.69475,0.77201,0.68101,0.45363,0.42174,0.87846,0.00084952,0.00084952,0.00084952
+78,35804.2,0.46361,0.41818,0.9219,0.79895,0.69762,0.77107,0.68005,0.45401,0.42224,0.87876,0.00084754,0.00084754,0.00084754
+79,36261.3,0.46416,0.41925,0.92238,0.76515,0.72391,0.76805,0.6782,0.45346,0.42263,0.87855,0.00084556,0.00084556,0.00084556
+80,36718,0.46402,0.41817,0.92145,0.76437,0.72538,0.76851,0.67819,0.4533,0.4224,0.87875,0.00084358,0.00084358,0.00084358
+81,37175.1,0.46216,0.41539,0.92017,0.76568,0.72454,0.76822,0.67813,0.45346,0.42295,0.87895,0.0008416,0.0008416,0.0008416
+82,37631.6,0.46253,0.41288,0.92032,0.77806,0.71767,0.76966,0.67924,0.45352,0.42376,0.87891,0.00083962,0.00083962,0.00083962
+83,38089.1,0.45927,0.41287,0.91951,0.7818,0.7217,0.76831,0.67754,0.4534,0.42399,0.87897,0.00083764,0.00083764,0.00083764
+84,38545.8,0.45915,0.41203,0.92189,0.78707,0.71863,0.76771,0.67804,0.45279,0.42425,0.87869,0.00083566,0.00083566,0.00083566
+85,39002.6,0.45858,0.40899,0.92037,0.79273,0.72032,0.76862,0.67897,0.45243,0.42485,0.87879,0.00083368,0.00083368,0.00083368
+86,39459.3,0.45864,0.40922,0.91975,0.78657,0.72246,0.76958,0.67928,0.45183,0.42487,0.87864,0.0008317,0.0008317,0.0008317
+87,39916.5,0.45708,0.40611,0.91709,0.78493,0.72216,0.77005,0.67945,0.45196,0.42528,0.87889,0.00082972,0.00082972,0.00082972
+88,40373.2,0.45586,0.40475,0.9177,0.7873,0.72054,0.76952,0.6804,0.45172,0.42557,0.87891,0.00082774,0.00082774,0.00082774
+89,40830.3,0.45607,0.40352,0.91685,0.78946,0.72047,0.77068,0.68128,0.45137,0.42593,0.8786,0.00082576,0.00082576,0.00082576
+90,41287,0.45555,0.40366,0.91769,0.78649,0.72242,0.77133,0.68226,0.45131,0.42603,0.8788,0.00082378,0.00082378,0.00082378
+91,41743.7,0.45334,0.40325,0.91687,0.78225,0.72174,0.77248,0.6835,0.45121,0.42558,0.87871,0.0008218,0.0008218,0.0008218
+92,42200.1,0.4523,0.3988,0.91459,0.78005,0.71967,0.77139,0.68284,0.45084,0.42535,0.87843,0.00081982,0.00081982,0.00081982
+93,42657.3,0.45389,0.39987,0.91523,0.77945,0.72395,0.76969,0.68103,0.45064,0.42562,0.87839,0.00081784,0.00081784,0.00081784
+94,43114.3,0.45189,0.39892,0.91509,0.77935,0.72389,0.76837,0.68026,0.45048,0.42592,0.87853,0.00081586,0.00081586,0.00081586
+95,43571,0.45095,0.39702,0.91544,0.78362,0.7192,0.76941,0.68133,0.45038,0.42666,0.87875,0.00081388,0.00081388,0.00081388
+96,44027.8,0.45043,0.39434,0.9143,0.78529,0.72434,0.76974,0.68066,0.4502,0.42693,0.87872,0.0008119,0.0008119,0.0008119
+97,44485,0.44907,0.39346,0.91497,0.78972,0.72503,0.77126,0.68284,0.45032,0.42606,0.87929,0.00080992,0.00080992,0.00080992
+98,44941.6,0.4501,0.39176,0.91463,0.79343,0.7235,0.77175,0.68363,0.4496,0.42576,0.8788,0.00080794,0.00080794,0.00080794
+99,45398.3,0.4472,0.39053,0.91264,0.78797,0.7241,0.77215,0.68449,0.44971,0.42459,0.87906,0.00080596,0.00080596,0.00080596
+100,45854.9,0.44797,0.39095,0.91435,0.79764,0.71761,0.77162,0.68358,0.44971,0.42364,0.87945,0.00080398,0.00080398,0.00080398
+101,46312.2,0.44859,0.38778,0.91432,0.79517,0.7157,0.77186,0.68362,0.44986,0.42318,0.88002,0.000802,0.000802,0.000802
+102,46769.3,0.44737,0.38979,0.91256,0.79498,0.71184,0.77005,0.68133,0.44934,0.42342,0.87958,0.00080002,0.00080002,0.00080002
+103,47226.3,0.44651,0.39091,0.9139,0.80105,0.70571,0.77037,0.68103,0.4489,0.42247,0.87931,0.00079804,0.00079804,0.00079804
+104,47683.2,0.44593,0.38576,0.91242,0.79937,0.70537,0.76903,0.68048,0.4488,0.4227,0.87918,0.00079606,0.00079606,0.00079606
+105,48140,0.44384,0.38419,0.91217,0.79167,0.70701,0.76807,0.67955,0.44872,0.42306,0.8795,0.00079408,0.00079408,0.00079408
+106,48596.6,0.44397,0.38284,0.91164,0.79326,0.70713,0.76659,0.67955,0.44855,0.42309,0.87927,0.0007921,0.0007921,0.0007921
+107,49053.9,0.44312,0.38283,0.91175,0.76835,0.72471,0.76487,0.67789,0.44841,0.4238,0.87918,0.00079012,0.00079012,0.00079012
+108,49510.8,0.44293,0.38274,0.91101,0.80969,0.6922,0.76355,0.67723,0.44833,0.42412,0.87931,0.00078814,0.00078814,0.00078814
+109,49967.4,inf,0.38063,0.90988,0.81147,0.69346,0.76203,0.67542,0.44789,0.42471,0.87914,0.00078616,0.00078616,0.00078616
+110,50424.1,0.44198,0.38007,0.90952,0.81468,0.69532,0.76076,0.67456,0.44781,0.42463,0.87923,0.00078418,0.00078418,0.00078418
+111,50880.9,0.44111,0.37779,0.90967,0.81108,0.69234,0.75889,0.67367,0.44788,0.42456,0.8794,0.0007822,0.0007822,0.0007822
+112,51337.8,0.44019,0.37729,0.90865,0.8026,0.69656,0.75878,0.67267,0.44748,0.4252,0.87944,0.00078022,0.00078022,0.00078022
+113,51794.9,0.44043,0.37656,0.90976,0.78372,0.7083,0.76074,0.67461,0.44746,0.4256,0.87976,0.00077824,0.00077824,0.00077824
+114,52251.7,0.43925,0.37616,0.90879,0.77615,0.70974,0.75946,0.67339,0.44721,0.42609,0.87991,0.00077626,0.00077626,0.00077626
+115,52708.4,0.43886,0.37515,0.90909,0.78646,0.70411,0.75797,0.67266,0.44755,0.42701,0.88027,0.00077428,0.00077428,0.00077428
+116,53165,0.43715,0.37307,0.90821,0.78496,0.70646,0.7562,0.67198,0.44714,0.42773,0.88016,0.0007723,0.0007723,0.0007723
+117,53622,0.43647,0.37361,0.90851,0.78533,0.70883,0.75648,0.67042,0.44714,0.42884,0.88031,0.00077032,0.00077032,0.00077032
+118,54079.1,0.43673,0.37222,0.90782,0.78882,0.70904,0.75651,0.67085,0.44741,0.42964,0.88068,0.00076834,0.00076834,0.00076834
+119,54536,0.43743,0.37078,0.90754,0.78309,0.71043,0.7564,0.67002,0.44741,0.42995,0.88094,0.00076636,0.00076636,0.00076636
+120,54992.3,0.43669,0.37062,0.90803,0.7753,0.71363,0.75385,0.66899,0.44744,0.42999,0.88135,0.00076438,0.00076438,0.00076438
+121,55449,0.4334,0.36937,0.9063,0.75993,0.71958,0.75377,0.66952,0.44729,0.43001,0.88123,0.0007624,0.0007624,0.0007624
+122,55905.5,0.43429,0.36782,0.90624,0.78227,0.71082,0.75477,0.67058,0.44722,0.43052,0.88107,0.00076042,0.00076042,0.00076042
+123,56361.9,0.43469,0.36758,0.90525,0.78583,0.71081,0.75801,0.67238,0.44749,0.43031,0.88172,0.00075844,0.00075844,0.00075844
+124,56818.7,0.43462,0.36938,0.90565,0.77139,0.72738,0.75849,0.67203,0.4475,0.4298,0.88158,0.00075646,0.00075646,0.00075646
+125,57275.2,0.43339,0.36394,0.90478,0.76959,0.72729,0.75694,0.67113,0.44741,0.43019,0.88165,0.00075448,0.00075448,0.00075448
+126,57732,0.43394,0.36448,0.90473,0.76693,0.72795,0.75688,0.67172,0.44695,0.42989,0.88112,0.0007525,0.0007525,0.0007525
+127,58189.2,0.43253,0.36469,0.90486,0.76826,0.72626,0.75508,0.67017,0.44693,0.42962,0.88127,0.00075052,0.00075052,0.00075052
+128,58646.1,0.43239,0.36374,0.90486,0.76666,0.72359,0.75467,0.66914,0.44678,0.4302,0.88114,0.00074854,0.00074854,0.00074854
+129,59103.1,0.43185,0.36314,0.90531,0.76291,0.72795,0.75327,0.66787,0.44668,0.4322,0.88144,0.00074656,0.00074656,0.00074656
+130,59559.7,0.43216,0.36144,0.905,0.75751,0.72855,0.75448,0.66962,0.44644,0.43195,0.88184,0.00074458,0.00074458,0.00074458
+131,60016.9,0.43098,0.36052,0.90641,0.76098,0.73172,0.75348,0.66778,0.44635,0.43226,0.88217,0.0007426,0.0007426,0.0007426
+132,60473.4,0.43107,0.36141,0.90544,0.7615,0.73175,0.75313,0.6673,0.44648,0.43262,0.88259,0.00074062,0.00074062,0.00074062
+133,60929.8,0.42975,0.3596,0.90564,0.77032,0.72718,0.75407,0.66704,0.44623,0.43226,0.88259,0.00073864,0.00073864,0.00073864
+134,61386.8,0.42853,0.35903,0.90297,0.7678,0.71816,0.75102,0.66464,0.44645,0.43118,0.88286,0.00073666,0.00073666,0.00073666
+135,61844,0.42759,0.35641,0.90307,0.77209,0.72126,0.75152,0.665,0.44621,0.4314,0.88258,0.00073468,0.00073468,0.00073468
+136,62300.6,0.42683,0.35587,0.90236,0.77269,0.7198,0.7507,0.66488,0.4463,0.43073,0.88273,0.0007327,0.0007327,0.0007327
+137,62757.6,0.42793,0.35752,0.90495,0.75066,0.73559,0.75081,0.66467,0.44612,0.43051,0.88277,0.00073072,0.00073072,0.00073072
+138,63213.9,0.42776,0.35659,0.90466,0.7662,0.71974,0.75074,0.66386,0.44603,0.42897,0.88269,0.00072874,0.00072874,0.00072874
+139,63670.7,0.42712,0.35382,0.90171,0.75651,0.7333,0.75219,0.66594,0.44645,0.43025,0.88289,0.00072676,0.00072676,0.00072676
+140,64127.5,0.42492,0.35263,0.90012,0.76756,0.73341,0.75203,0.66597,0.4459,0.42972,0.88227,0.00072478,0.00072478,0.00072478
+141,64583.9,0.42503,0.35342,0.90313,0.76668,0.73627,0.7521,0.66657,0.44533,0.42909,0.88172,0.0007228,0.0007228,0.0007228
+142,65044.8,0.42461,0.34968,0.90277,0.76568,0.73795,0.75339,0.66688,0.44561,0.42896,0.8817,0.00072082,0.00072082,0.00072082
+143,65508.3,0.42521,0.35163,0.90093,0.75986,0.73199,0.75521,0.6692,0.44553,0.42939,0.88175,0.00071884,0.00071884,0.00071884
+144,65971.9,0.42471,0.35297,0.89987,0.75769,0.73147,0.75438,0.66957,0.44525,0.42913,0.88107,0.00071686,0.00071686,0.00071686
+145,66435.6,0.42376,0.34929,0.90032,0.74797,0.74298,0.75231,0.66701,0.44528,0.42973,0.88125,0.00071488,0.00071488,0.00071488
+146,66899.6,0.4228,0.34943,0.90095,0.74808,0.74264,0.7509,0.66617,0.44551,0.42927,0.88129,0.0007129,0.0007129,0.0007129
+147,67363.4,0.42311,0.35028,0.9019,0.75525,0.73759,0.75126,0.66572,0.44516,0.42961,0.88102,0.00071092,0.00071092,0.00071092
+148,67827,0.42366,0.34835,0.90192,0.76592,0.73358,0.75174,0.66591,0.44523,0.42977,0.88092,0.00070894,0.00070894,0.00070894

fashion_yolo/fashionpedia_exp/yolov8m_fashion+face_nohood/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_custom.yaml
+epochs: 500
+time: null
+patience: 50
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fashionpedia_exp
+name: yolov8m_fashion+face_nohood
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion+face_nohood

fashion_yolo/fashionpedia_exp/yolov8m_fashion+face_nohood/results.csv

@@ -0,0 +1,105 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,418.69,0.83535,1.13359,1.12916,0.58355,0.38296,0.40049,0.29072,0.85198,0.9464,1.0743,0.0670195,0.000333136,0.000333136
+2,832.244,0.78027,0.98155,1.09921,0.55347,0.49267,0.49226,0.38532,0.73881,0.76766,1.01008,0.0340182,0.00066515,0.00066515
+3,1245.36,0.7607,0.93537,1.0859,0.68314,0.48416,0.54006,0.42267,0.70499,0.71713,0.99057,0.00101557,0.000995844,0.000995844
+4,1658.08,0.72934,0.88177,1.06589,0.68385,0.52174,0.55965,0.45334,0.64942,0.65696,0.95469,0.00099406,0.00099406,0.00099406
+5,2071.43,0.69259,0.82831,1.04611,0.65451,0.55879,0.60955,0.49802,0.61654,0.5991,0.94472,0.00099208,0.00099208,0.00099208
+6,2484.93,0.67132,0.79942,1.03475,0.63809,0.58909,0.64498,0.53898,0.58812,0.57445,0.93224,0.0009901,0.0009901,0.0009901
+7,2897.63,0.65372,0.77202,1.02463,0.63581,0.63464,0.65829,0.55615,0.56852,0.5483,0.92767,0.00098812,0.00098812,0.00098812
+8,3310.61,0.6412,0.74848,1.01886,0.66535,0.62042,0.6565,0.55715,0.54634,0.54175,0.91201,0.00098614,0.00098614,0.00098614
+9,3723.44,0.62663,0.72925,1.01312,0.69047,0.6491,0.69149,0.58896,0.53693,0.51058,0.91197,0.00098416,0.00098416,0.00098416
+10,4136.15,0.61641,0.71197,1.00549,0.65905,0.68377,0.70796,0.60279,0.52556,0.50095,0.90775,0.00098218,0.00098218,0.00098218
+11,4549.15,0.60951,0.70123,1.00254,0.77429,0.63249,0.72609,0.62208,0.51859,0.49194,0.90477,0.0009802,0.0009802,0.0009802
+12,4962.01,0.60036,0.68476,0.99667,0.69273,0.70661,0.7192,0.61669,0.51307,0.48322,0.89946,0.00097822,0.00097822,0.00097822
+13,5374.93,0.59331,0.67326,0.99298,0.73702,0.69096,0.73417,0.63361,0.5005,0.4701,0.89502,0.00097624,0.00097624,0.00097624
+14,5787.98,0.58571,0.66051,0.99001,0.73696,0.68337,0.73469,0.63523,0.49345,0.46298,0.89208,0.00097426,0.00097426,0.00097426
+15,6200.77,0.58228,0.65152,0.98736,0.73404,0.69448,0.74113,0.64559,0.491,0.45165,0.89195,0.00097228,0.00097228,0.00097228
+16,6613.85,0.57727,0.64241,0.98396,0.74017,0.69424,0.74893,0.65076,0.48925,0.44772,0.89293,0.0009703,0.0009703,0.0009703
+17,7026.99,0.57085,0.63401,0.98151,0.75499,0.69208,0.75606,0.66141,0.48373,0.44486,0.88987,0.00096832,0.00096832,0.00096832
+18,7445.77,0.56534,0.62296,0.978,0.74671,0.69906,0.75604,0.66082,0.48111,0.44055,0.88891,0.00096634,0.00096634,0.00096634
+19,7858.49,0.56234,0.6184,0.97754,0.80391,0.67185,0.76344,0.66695,0.47915,0.43924,0.88837,0.00096436,0.00096436,0.00096436
+20,8271.55,0.55967,0.61063,0.97563,0.7756,0.69819,0.76841,0.67156,0.47659,0.43795,0.88744,0.00096238,0.00096238,0.00096238
+21,8687.45,0.55412,0.59943,0.96952,0.76666,0.70382,0.77489,0.67666,0.47599,0.43572,0.88665,0.0009604,0.0009604,0.0009604
+22,9100.4,0.55025,0.59563,0.97045,0.80411,0.69054,0.77823,0.6801,0.47403,0.43469,0.8854,0.00095842,0.00095842,0.00095842
+23,9513.34,0.54722,0.58926,0.96809,0.82337,0.68518,0.77857,0.68263,0.47328,0.43322,0.88533,0.00095644,0.00095644,0.00095644
+24,9926.52,0.54295,0.58363,0.96584,0.80297,0.68982,0.78083,0.68564,0.47136,0.43154,0.8842,0.00095446,0.00095446,0.00095446
+25,10339.4,0.53974,0.57646,0.96407,0.7699,0.70073,0.78134,0.68691,0.47007,0.43053,0.88364,0.00095248,0.00095248,0.00095248
+26,10770.4,0.53886,0.57003,0.96211,0.73863,0.73039,0.78149,0.68724,0.46886,0.42886,0.88288,0.0009505,0.0009505,0.0009505
+27,11203.6,0.53694,0.56648,0.96211,0.7222,0.74507,0.78238,0.68769,0.46738,0.42755,0.88182,0.00094852,0.00094852,0.00094852
+28,11616.8,0.53234,0.55959,0.96062,0.72502,0.74511,0.78305,0.68868,0.46601,0.42598,0.88155,0.00094654,0.00094654,0.00094654
+29,12029.6,0.53086,0.55749,0.95804,0.73893,0.73204,0.78328,0.6894,0.46503,0.42523,0.88086,0.00094456,0.00094456,0.00094456
+30,12442.9,0.52916,0.55384,0.96024,0.75173,0.71998,0.78268,0.68942,0.46429,0.42449,0.88069,0.00094258,0.00094258,0.00094258
+31,12856.1,0.52605,0.54554,0.95641,0.74954,0.73451,0.78353,0.68962,0.46374,0.42358,0.88029,0.0009406,0.0009406,0.0009406
+32,13269.5,0.5259,0.54455,0.95655,0.74595,0.74918,0.78427,0.69016,0.46307,0.42256,0.87995,0.00093862,0.00093862,0.00093862
+33,13682.7,0.52076,0.53968,0.95476,0.75051,0.75022,0.78912,0.69416,0.46215,0.42184,0.87972,0.00093664,0.00093664,0.00093664
+34,14095.7,0.51925,0.53408,0.95289,0.76244,0.73852,0.79142,0.69639,0.46139,0.42097,0.87926,0.00093466,0.00093466,0.00093466
+35,14508.7,0.51796,0.53128,0.95296,0.76476,0.74462,0.79161,0.69824,0.46064,0.42113,0.87856,0.00093268,0.00093268,0.00093268
+36,14921.9,0.5146,0.52453,0.95148,0.76498,0.73775,0.79006,0.69735,0.45998,0.41975,0.87822,0.0009307,0.0009307,0.0009307
+37,15334.5,0.51386,0.52272,0.95084,0.76097,0.74416,0.79441,0.70134,0.45932,0.41943,0.87796,0.00092872,0.00092872,0.00092872
+38,15747.8,0.51141,0.51925,0.94828,0.76252,0.73061,0.79557,0.70253,0.45847,0.41881,0.87747,0.00092674,0.00092674,0.00092674
+39,16160.9,0.51017,0.51475,0.94806,0.78945,0.71704,0.79672,0.70384,0.45772,0.41778,0.87718,0.00092476,0.00092476,0.00092476
+40,16574.1,0.50964,0.51421,0.94737,0.78623,0.72013,0.79745,0.70409,0.45721,0.41756,0.87691,0.00092278,0.00092278,0.00092278
+41,16987.3,0.50727,0.50681,0.94581,0.77233,0.72869,0.80081,0.70669,0.45646,0.41774,0.87651,0.0009208,0.0009208,0.0009208
+42,17400.8,0.50444,0.50368,0.94476,0.7724,0.73005,0.80087,0.70645,0.45593,0.41723,0.87636,0.00091882,0.00091882,0.00091882
+43,17817.2,0.50331,0.50043,0.94272,0.78011,0.72365,0.80025,0.70637,0.45531,0.41667,0.87577,0.00091684,0.00091684,0.00091684
+44,18230.2,0.49997,0.49976,0.94246,0.76128,0.73765,0.79881,0.70533,0.45447,0.4164,0.87496,0.00091486,0.00091486,0.00091486
+45,18643.5,0.50128,0.49564,0.94259,0.80039,0.71037,0.80016,0.7073,0.45293,0.4157,0.8741,0.00091288,0.00091288,0.00091288
+46,19057,0.4993,0.49319,0.94164,0.76954,0.73201,0.79752,0.70481,0.45216,0.41622,0.87362,0.0009109,0.0009109,0.0009109
+47,19470,0.49727,0.49241,0.94068,0.7627,0.74122,0.79872,0.70583,0.45167,0.41558,0.8735,0.00090892,0.00090892,0.00090892
+48,19883.1,0.49796,0.48956,0.94143,0.76406,0.73882,0.79846,0.70615,0.45138,0.41527,0.87353,0.00090694,0.00090694,0.00090694
+49,20296.5,0.49546,0.48413,0.94004,0.77804,0.73915,0.79651,0.7049,0.45036,0.41469,0.873,0.00090496,0.00090496,0.00090496
+50,20709.9,0.49374,0.48193,0.93856,0.75715,0.74998,0.79761,0.70672,0.44862,0.41322,0.87172,0.00090298,0.00090298,0.00090298
+51,21123,0.49173,0.48042,0.93761,0.75312,0.76114,0.80086,0.70989,0.4478,0.41251,0.87141,0.000901,0.000901,0.000901
+52,21536.1,0.4925,0.47896,0.93668,0.75894,0.75716,0.79916,0.70979,0.44683,0.41208,0.8711,0.00089902,0.00089902,0.00089902
+53,21949.3,0.49059,0.47373,0.93603,0.75033,0.75753,0.79993,0.71,0.44632,0.41236,0.87075,0.00089704,0.00089704,0.00089704
+54,22362.7,0.48891,0.47249,0.93646,0.74364,0.76568,0.79959,0.71227,0.44535,0.41234,0.87075,0.00089506,0.00089506,0.00089506
+55,22776.2,0.48682,0.46793,0.93362,0.74023,0.76995,0.79986,0.71232,0.44468,0.41223,0.87038,0.00089308,0.00089308,0.00089308
+56,23189.5,0.48631,0.46959,0.93358,0.75056,0.76026,0.80061,0.71176,0.44416,0.4118,0.8703,0.0008911,0.0008911,0.0008911
+57,23607.7,0.48619,0.46501,0.93519,0.7537,0.76494,0.79862,0.71104,0.44394,0.41235,0.87053,0.00088912,0.00088912,0.00088912
+58,24020.7,0.48476,0.46277,0.93324,0.75743,0.76102,0.79932,0.71131,0.44358,0.41228,0.87041,0.00088714,0.00088714,0.00088714
+59,24433.8,0.48166,0.46254,0.93205,0.76176,0.75102,0.79827,0.709,0.44337,0.41178,0.87058,0.00088516,0.00088516,0.00088516
+60,24847.1,0.48212,0.45845,0.93135,0.76823,0.75006,0.79928,0.71042,0.44323,0.41134,0.87067,0.00088318,0.00088318,0.00088318
+61,25260.4,0.47819,0.45481,0.92939,0.78356,0.73803,0.79808,0.7088,0.44319,0.41177,0.87088,0.0008812,0.0008812,0.0008812
+62,25676.3,0.48044,0.4541,0.92984,0.79393,0.73299,0.79838,0.70863,0.44272,0.41204,0.8708,0.00087922,0.00087922,0.00087922
+63,26089.6,0.47791,0.45112,0.92915,0.78968,0.73772,0.79925,0.71099,0.44254,0.41099,0.87055,0.00087724,0.00087724,0.00087724
+64,26502.8,0.47806,0.44986,0.92901,0.80092,0.732,0.80017,0.71352,0.44219,0.41138,0.87009,0.00087526,0.00087526,0.00087526
+65,26915.6,0.476,0.4468,0.92896,0.78978,0.73796,0.79886,0.71154,0.44215,0.4119,0.86973,0.00087328,0.00087328,0.00087328
+66,27322.5,0.47772,0.44785,0.92943,0.79266,0.73314,0.79866,0.71153,0.44217,0.41167,0.86992,0.0008713,0.0008713,0.0008713
+67,27729.6,0.47233,0.44218,0.92638,0.78418,0.73931,0.79885,0.71062,0.44223,0.41196,0.8701,0.00086932,0.00086932,0.00086932
+68,28136.5,0.47261,0.44138,0.92722,0.78131,0.7393,0.80012,0.71136,0.44195,0.41121,0.87033,0.00086734,0.00086734,0.00086734
+69,28543.3,0.47434,0.44198,0.92755,0.76545,0.75512,0.80294,0.71495,0.4414,0.41223,0.8702,0.00086536,0.00086536,0.00086536
+70,28950,0.47358,0.44024,0.92585,0.77268,0.75158,0.80198,0.71476,0.44142,0.41306,0.87043,0.00086338,0.00086338,0.00086338
+71,29357.1,0.47182,0.44245,0.927,0.77147,0.75214,0.80304,0.71586,0.44129,0.41262,0.8709,0.0008614,0.0008614,0.0008614
+72,29764.1,0.4699,0.43587,0.92728,0.75905,0.75395,0.80313,0.71603,0.44134,0.41219,0.87116,0.00085942,0.00085942,0.00085942
+73,30171.5,0.47064,0.43401,0.92513,0.75106,0.75756,0.80196,0.71564,0.44075,0.41377,0.87084,0.00085744,0.00085744,0.00085744
+74,30578.8,0.46963,0.43396,0.92446,0.74647,0.76236,0.79796,0.71287,0.44047,0.41486,0.87063,0.00085546,0.00085546,0.00085546
+75,30986,0.46753,0.4297,0.92304,0.74813,0.76113,0.79784,0.71295,0.44099,0.41523,0.87126,0.00085348,0.00085348,0.00085348
+76,31393.1,0.46816,0.42883,0.92469,0.75173,0.76017,0.79417,0.70999,0.44127,0.41529,0.87185,0.0008515,0.0008515,0.0008515
+77,31800,0.46755,0.42557,0.9221,0.75028,0.75999,0.79398,0.70994,0.44089,0.41509,0.87155,0.00084952,0.00084952,0.00084952
+78,32207.2,0.46605,0.42535,0.92224,0.74602,0.76574,0.79463,0.71033,0.44037,0.41484,0.8715,0.00084754,0.00084754,0.00084754
+79,32614.3,0.46419,0.42386,0.92196,0.74853,0.7638,0.79435,0.71007,0.44025,0.41418,0.87156,0.00084556,0.00084556,0.00084556
+80,33021.3,0.46331,0.42135,0.92009,0.74608,0.76806,0.79346,0.71001,0.44013,0.41416,0.87146,0.00084358,0.00084358,0.00084358
+81,33428.3,0.46329,0.42098,0.9203,0.73533,0.77353,0.79369,0.70978,0.44014,0.41412,0.87161,0.0008416,0.0008416,0.0008416
+82,33838.2,0.46204,0.41945,0.9202,0.72866,0.76873,0.79184,0.70796,0.43985,0.41397,0.87148,0.00083962,0.00083962,0.00083962
+83,34245.4,0.46047,0.4179,0.9196,0.73688,0.764,0.79546,0.71093,0.43961,0.41322,0.87154,0.00083764,0.00083764,0.00083764
+84,34652.4,0.46059,0.41616,0.91913,0.757,0.7515,0.79431,0.71142,0.43956,0.41412,0.87181,0.00083566,0.00083566,0.00083566
+85,35059.2,0.45804,0.41332,0.91884,0.75192,0.75519,0.79216,0.71057,0.43903,0.4147,0.87125,0.00083368,0.00083368,0.00083368
+86,35465.6,0.45891,0.4142,0.91914,0.74396,0.75136,0.79133,0.7107,0.43902,0.41553,0.87161,0.0008317,0.0008317,0.0008317
+87,35872.3,0.45788,0.41118,0.91874,0.7342,0.7607,0.78855,0.70827,0.43848,0.41534,0.87155,0.00082972,0.00082972,0.00082972
+88,36279.4,0.45947,0.41375,0.91884,0.74042,0.75982,0.78883,0.70845,0.43781,0.4151,0.87105,0.00082774,0.00082774,0.00082774
+89,36686.3,0.45737,0.40988,0.91824,0.74366,0.75101,0.78688,0.70468,0.43765,0.41532,0.87122,0.00082576,0.00082576,0.00082576
+90,37093.4,0.45558,0.40892,0.91977,0.74055,0.74452,0.78835,0.70488,0.43702,0.41471,0.87083,0.00082378,0.00082378,0.00082378
+91,37500.1,0.45482,0.40572,0.91678,0.71077,0.7772,0.78449,0.70238,0.43658,0.4165,0.87078,0.0008218,0.0008218,0.0008218
+92,37906.9,0.45494,0.40508,0.91603,0.75222,0.74549,0.78572,0.70291,0.43645,0.41604,0.87073,0.00081982,0.00081982,0.00081982
+93,38313.7,0.45338,0.40396,0.91692,0.75845,0.73926,0.78497,0.70213,0.43607,0.41614,0.87065,0.00081784,0.00081784,0.00081784
+94,38720.6,0.45335,0.40144,0.91629,0.77968,0.72014,0.78322,0.69995,0.43559,0.41663,0.87041,0.00081586,0.00081586,0.00081586
+95,39127.2,0.4518,0.40143,0.9156,0.73032,0.7702,0.77981,0.69603,0.43578,0.41742,0.87058,0.00081388,0.00081388,0.00081388
+96,39533.9,0.45207,0.4002,0.91584,0.73874,0.76339,0.78094,0.69774,0.43591,0.41834,0.87081,0.0008119,0.0008119,0.0008119
+97,39940.6,0.45152,0.39845,0.91479,0.78103,0.7198,0.78089,0.69749,0.43635,0.41902,0.87149,0.00080992,0.00080992,0.00080992
+98,40347.3,0.44954,0.39821,0.91471,0.7782,0.72363,0.78284,0.69964,0.43642,0.41986,0.87176,0.00080794,0.00080794,0.00080794
+99,40754.4,0.44988,0.39499,0.91411,0.77651,0.72593,0.78467,0.70062,0.43628,0.42137,0.8718,0.00080596,0.00080596,0.00080596
+100,41161.2,0.44889,0.3957,0.91274,0.75338,0.74382,0.78477,0.70181,0.43602,0.42178,0.87143,0.00080398,0.00080398,0.00080398
+101,41568,0.44779,0.39306,0.91275,0.75099,0.74695,0.7843,0.70103,0.43644,0.42216,0.87127,0.000802,0.000802,0.000802
+102,41975.1,0.44856,0.39426,0.91325,0.75858,0.73667,0.7809,0.69774,0.43662,0.42299,0.87155,0.00080002,0.00080002,0.00080002
+103,42382,0.44735,0.39378,0.91381,0.76037,0.73623,0.78,0.69653,0.43668,0.42338,0.87169,0.00079804,0.00079804,0.00079804
+104,42788.9,0.44689,0.39126,0.91246,0.74343,0.74803,0.77881,0.69503,0.43682,0.42335,0.87165,0.00079606,0.00079606,0.00079606

fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_bak.yaml
+epochs: 300
+time: null
+patience: 50
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fashionpedia_exp
+name: yolov8m_fashion_all
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_all

fashion_yolo/fashionpedia_exp/yolov8m_fashion_all/results.csv

@@ -0,0 +1,105 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,423.272,1.11804,1.48533,1.24553,0.55,0.26673,0.25707,0.17107,1.16457,1.42309,1.25638,0.0670202,0.000333129,0.000333129
+2,840.821,1.07037,1.25643,1.21377,0.53272,0.34092,0.35016,0.2431,1.03132,1.08857,1.17762,0.034018,0.000664263,0.000664263
+3,1257.38,1.04423,1.18909,1.19634,0.58003,0.35043,0.36787,0.26313,0.99679,1.02316,1.15343,0.00101365,0.000993197,0.000993197
+4,1673.82,1.00647,1.11537,1.17171,0.55406,0.39638,0.40526,0.2965,0.94548,0.93585,1.11311,0.0009901,0.0009901,0.0009901
+5,2090.38,0.97138,1.05029,1.15031,0.59595,0.40732,0.43596,0.32105,0.90757,0.89195,1.09525,0.0009868,0.0009868,0.0009868
+6,2506.59,0.94497,1.00603,1.13383,0.64868,0.40786,0.44323,0.33174,0.88859,0.84335,1.08578,0.0009835,0.0009835,0.0009835
+7,2923.08,0.92564,0.97481,1.12234,0.65689,0.42494,0.4649,0.3534,0.85642,0.8164,1.06716,0.0009802,0.0009802,0.0009802
+8,3339.6,0.90909,0.94347,1.11224,0.63848,0.42443,0.47592,0.35961,0.8487,0.78128,1.05486,0.0009769,0.0009769,0.0009769
+9,3756.01,0.89516,0.91892,1.10343,0.69973,0.44769,0.49843,0.38387,0.82817,0.76073,1.04908,0.0009736,0.0009736,0.0009736
+10,4172.3,0.88575,0.90029,1.09692,0.61612,0.47757,0.49803,0.38389,0.81523,0.74462,1.03997,0.0009703,0.0009703,0.0009703
+11,4588.8,0.87504,0.88374,1.09055,0.66866,0.46711,0.50611,0.38849,0.80635,0.72838,1.03532,0.000967,0.000967,0.000967
+12,5005.39,0.86584,0.86517,1.08645,0.66044,0.47761,0.51259,0.39859,0.80069,0.71077,1.03119,0.0009637,0.0009637,0.0009637
+13,5421.27,0.85928,0.85385,1.0815,0.64495,0.48769,0.52093,0.40611,0.79041,0.70016,1.02656,0.0009604,0.0009604,0.0009604
+14,5837.21,0.85239,0.83961,1.07615,0.65564,0.4919,0.52842,0.41299,0.78587,0.69185,1.02196,0.0009571,0.0009571,0.0009571
+15,6253.65,0.84563,0.82737,1.07137,0.56095,0.52905,0.53188,0.41613,0.78111,0.68483,1.0185,0.0009538,0.0009538,0.0009538
+16,6670.18,0.84027,0.81615,1.06991,0.61213,0.51121,0.53901,0.42027,0.77819,0.67904,1.01714,0.0009505,0.0009505,0.0009505
+17,7086.54,0.83301,0.8069,1.06665,0.61937,0.52332,0.54373,0.42679,0.77574,0.67352,1.01628,0.0009472,0.0009472,0.0009472
+18,7503.23,0.82938,0.79701,1.06196,0.60429,0.54006,0.54873,0.43032,0.77035,0.6686,1.01274,0.0009439,0.0009439,0.0009439
+19,7920.06,0.82429,0.78797,1.05985,0.60365,0.53738,0.54911,0.43311,0.76634,0.66542,1.0101,0.0009406,0.0009406,0.0009406
+20,8340.15,0.81808,0.77603,1.05516,0.62821,0.52777,0.55339,0.43479,0.76488,0.65991,1.00914,0.0009373,0.0009373,0.0009373
+21,8756.4,0.81396,0.76921,1.05319,0.59172,0.54578,0.55009,0.43164,0.76265,0.65798,1.00884,0.000934,0.000934,0.000934
+22,9172.6,0.81014,0.76035,1.05008,0.59012,0.53698,0.54707,0.43129,0.76103,0.65588,1.00833,0.0009307,0.0009307,0.0009307
+23,9588.51,0.80568,0.75486,1.04971,0.60168,0.53635,0.55145,0.43471,0.75911,0.65384,1.00728,0.0009274,0.0009274,0.0009274
+24,10004.7,0.80139,0.74618,1.04613,0.59958,0.53801,0.55326,0.43806,0.75714,0.65129,1.00581,0.0009241,0.0009241,0.0009241
+25,10420.9,0.7978,0.74211,1.04536,0.62449,0.53635,0.55474,0.43831,0.75631,0.64906,1.00497,0.0009208,0.0009208,0.0009208
+26,10837.4,0.79528,0.73449,1.04164,0.63605,0.53384,0.55552,0.44099,0.75488,0.64754,1.00395,0.0009175,0.0009175,0.0009175
+27,11253.5,0.79075,0.72837,1.0388,0.63987,0.53375,0.55397,0.44004,0.75382,0.64507,1.00302,0.0009142,0.0009142,0.0009142
+28,11669.8,0.78667,0.72317,1.03767,0.6355,0.54046,0.55626,0.44196,0.75263,0.6427,1.00235,0.0009109,0.0009109,0.0009109
+29,12085.9,0.7866,0.7209,1.03741,0.64041,0.54434,0.55837,0.44339,0.75214,0.64107,1.00195,0.0009076,0.0009076,0.0009076
+30,12496.2,0.78208,0.71487,1.03461,0.63898,0.54922,0.55991,0.44429,0.75153,0.63903,1.00183,0.0009043,0.0009043,0.0009043
+31,12906.7,0.78115,0.71002,1.03384,0.64412,0.54747,0.56224,0.4454,0.75125,0.63683,1.00159,0.000901,0.000901,0.000901
+32,13317,0.77699,0.70108,1.03151,0.65986,0.53939,0.567,0.44978,0.75026,0.6357,1.00106,0.0008977,0.0008977,0.0008977
+33,13727.3,0.77535,0.69913,1.03055,0.64206,0.56155,0.57,0.45296,0.74904,0.63426,1.00034,0.0008944,0.0008944,0.0008944
+34,14137.7,0.77129,0.69369,1.02894,0.63568,0.55759,0.57311,0.45488,0.74735,0.63236,0.99948,0.0008911,0.0008911,0.0008911
+35,14548.1,0.76992,0.68841,1.02856,0.6324,0.56448,0.57376,0.45633,0.74607,0.63006,0.99897,0.0008878,0.0008878,0.0008878
+36,14958.2,0.76593,0.68384,1.02638,0.62909,0.5638,0.57579,0.45877,0.7451,0.62879,0.99878,0.0008845,0.0008845,0.0008845
+37,15368.3,0.76445,0.68161,1.02471,0.60819,0.55986,0.5756,0.45867,0.74458,0.62793,0.99885,0.0008812,0.0008812,0.0008812
+38,15778.5,0.76251,0.67843,1.02456,0.61289,0.56002,0.57464,0.45763,0.74355,0.62695,0.99828,0.0008779,0.0008779,0.0008779
+39,16188.9,0.7592,0.67096,1.02194,0.61614,0.55895,0.5756,0.45853,0.7425,0.62544,0.9977,0.0008746,0.0008746,0.0008746
+40,16599,0.75831,0.66992,1.02141,0.61776,0.55886,0.57776,0.46098,0.74138,0.62379,0.99725,0.0008713,0.0008713,0.0008713
+41,17009.6,0.75731,0.66643,1.02147,0.62515,0.5579,0.5781,0.46186,0.74017,0.62236,0.99673,0.000868,0.000868,0.000868
+42,17420,0.75458,0.66212,1.01902,0.62978,0.55591,0.57953,0.4631,0.73897,0.62079,0.99648,0.0008647,0.0008647,0.0008647
+43,17830.4,0.75223,0.65784,1.01701,0.63946,0.55466,0.58026,0.46272,0.73825,0.61965,0.99621,0.0008614,0.0008614,0.0008614
+44,18240.7,0.7493,0.65385,1.01597,0.63252,0.55549,0.58281,0.46439,0.73794,0.61861,0.99623,0.0008581,0.0008581,0.0008581
+45,18650.9,0.74636,0.64901,1.01488,0.63223,0.55666,0.58385,0.46423,0.73778,0.6177,0.9961,0.0008548,0.0008548,0.0008548
+46,19061,0.74588,0.64735,1.01344,0.63236,0.55954,0.58421,0.46472,0.73799,0.61658,0.99655,0.0008515,0.0008515,0.0008515
+47,19471.2,0.74496,0.64645,1.01411,0.62892,0.56955,0.58505,0.46638,0.73712,0.61578,0.99604,0.0008482,0.0008482,0.0008482
+48,19881.5,0.74294,0.64192,1.01247,0.62847,0.57009,0.58727,0.46842,0.73682,0.61516,0.99616,0.0008449,0.0008449,0.0008449
+49,20291.7,0.74067,0.63988,1.01018,0.65109,0.56945,0.5872,0.46858,0.73712,0.61464,0.99658,0.0008416,0.0008416,0.0008416
+50,20701.7,0.73754,0.63558,1.00985,0.65764,0.56653,0.5878,0.47019,0.73676,0.6137,0.99644,0.0008383,0.0008383,0.0008383
+51,21111.8,0.73674,0.63168,1.00902,0.63906,0.55753,0.58842,0.47075,0.73661,0.61332,0.99618,0.000835,0.000835,0.000835
+52,21522,0.73633,0.62923,1.00848,0.63235,0.56754,0.58923,0.47078,0.73546,0.61228,0.99531,0.0008317,0.0008317,0.0008317
+53,21932,0.73376,0.62668,1.00679,0.61277,0.56915,0.58976,0.47102,0.73427,0.61174,0.99452,0.0008284,0.0008284,0.0008284
+54,22342,0.73314,0.62566,1.00821,0.61985,0.56195,0.59067,0.47266,0.73331,0.61148,0.99418,0.0008251,0.0008251,0.0008251
+55,22752.4,0.73011,0.61848,1.00486,0.62353,0.56161,0.58978,0.471,0.73333,0.61089,0.99429,0.0008218,0.0008218,0.0008218
+56,23162.5,0.72865,0.61946,1.00492,0.63636,0.55107,0.58775,0.47005,0.733,0.61004,0.99443,0.0008185,0.0008185,0.0008185
+57,23572.6,0.72751,0.61457,1.00303,0.63114,0.55687,0.58844,0.47019,0.73279,0.60992,0.99432,0.0008152,0.0008152,0.0008152
+58,23982.7,0.72573,0.61133,1.0021,0.60145,0.56762,0.58748,0.46936,0.73232,0.60943,0.99384,0.0008119,0.0008119,0.0008119
+59,24392.9,0.72552,0.6103,1.00162,0.60527,0.56645,0.5875,0.46907,0.73265,0.60934,0.99406,0.0008086,0.0008086,0.0008086
+60,24803.3,0.72448,0.60779,1.00225,0.59358,0.57213,0.58675,0.46968,0.73268,0.60956,0.99438,0.0008053,0.0008053,0.0008053
+61,25213.3,0.72201,0.60537,1.0006,0.60078,0.57007,0.58518,0.46926,0.733,0.60976,0.99469,0.000802,0.000802,0.000802
+62,25623.4,0.72112,0.60085,1.00023,0.60742,0.56656,0.58485,0.46913,0.73274,0.61003,0.99466,0.0007987,0.0007987,0.0007987
+63,26033.5,0.71758,0.60017,0.99875,0.59854,0.56748,0.58636,0.46925,0.73258,0.61016,0.99463,0.0007954,0.0007954,0.0007954
+64,26443.8,0.71715,0.59841,0.99904,0.59846,0.56616,0.58669,0.46959,0.73231,0.61029,0.99474,0.0007921,0.0007921,0.0007921
+65,26853.8,0.71691,0.59505,0.9978,0.60926,0.56065,0.58485,0.4673,0.73209,0.6109,0.99473,0.0007888,0.0007888,0.0007888
+66,27264.1,0.71677,0.59351,0.99611,0.60223,0.56804,0.58475,0.46656,0.73187,0.61034,0.9945,0.0007855,0.0007855,0.0007855
+67,27674.1,0.71316,0.59057,0.99427,0.59928,0.56693,0.58358,0.46656,0.73204,0.61015,0.99485,0.0007822,0.0007822,0.0007822
+68,28084.2,0.71189,0.58878,0.99407,0.61673,0.55507,0.58163,0.46478,0.73195,0.61036,0.99488,0.0007789,0.0007789,0.0007789
+69,28494.1,0.71066,0.58626,0.99383,0.60563,0.56086,0.58158,0.46373,0.73211,0.61065,0.9951,0.0007756,0.0007756,0.0007756
+70,28904.1,0.71027,0.5854,0.99279,0.60943,0.55783,0.57942,0.46335,0.73193,0.61148,0.99527,0.0007723,0.0007723,0.0007723
+71,29314,0.71042,0.58246,0.99383,0.60752,0.55747,0.57731,0.46233,0.73202,0.61195,0.99545,0.000769,0.000769,0.000769
+72,29724.1,0.70936,0.58204,0.99266,0.6014,0.55801,0.57716,0.46119,0.73121,0.61196,0.99488,0.0007657,0.0007657,0.0007657
+73,30134.3,0.70641,0.57848,0.99147,0.60018,0.56144,0.57629,0.461,0.73054,0.61204,0.99449,0.0007624,0.0007624,0.0007624
+74,30544.1,0.70596,0.57837,0.99054,0.59549,0.56442,0.57589,0.46084,0.72959,0.61257,0.99409,0.0007591,0.0007591,0.0007591
+75,30954.3,0.70412,0.57449,0.98966,0.59922,0.56204,0.57362,0.45879,0.72944,0.61322,0.99398,0.0007558,0.0007558,0.0007558
+76,31364.2,0.70301,0.57244,0.99015,0.60298,0.55752,0.57468,0.46117,0.72919,0.61276,0.99405,0.0007525,0.0007525,0.0007525
+77,31774.2,0.7023,0.57249,0.98927,0.60336,0.55564,0.57274,0.45911,0.72905,0.61349,0.99431,0.0007492,0.0007492,0.0007492
+78,32183.9,0.70131,0.57191,0.98921,0.59972,0.55688,0.57172,0.45901,0.7285,0.61357,0.99442,0.0007459,0.0007459,0.0007459
+79,32593.9,0.6996,0.56764,0.9882,0.60475,0.55516,0.57241,0.45872,0.72866,0.61347,0.99426,0.0007426,0.0007426,0.0007426
+80,33003.9,0.69797,0.56562,0.98792,0.60385,0.55107,0.57159,0.45846,0.72914,0.6139,0.99445,0.0007393,0.0007393,0.0007393
+81,33413.9,0.69656,0.56416,0.98596,0.60748,0.54796,0.57153,0.45958,0.72982,0.61457,0.99502,0.000736,0.000736,0.000736
+82,33823.6,0.69523,0.56022,0.9856,0.60131,0.54144,0.57152,0.45858,0.73037,0.61492,0.99571,0.0007327,0.0007327,0.0007327
+83,34233.9,0.69415,0.55999,0.98587,0.59313,0.54856,0.57215,0.45822,0.73065,0.61518,0.99636,0.0007294,0.0007294,0.0007294
+84,34643.6,0.69417,0.55917,0.98452,0.5951,0.54482,0.57584,0.46094,0.73097,0.61567,0.99643,0.0007261,0.0007261,0.0007261
+85,35053.5,0.69462,0.55972,0.98437,0.5968,0.54578,0.5741,0.45978,0.7308,0.61608,0.99627,0.0007228,0.0007228,0.0007228
+86,35463.4,0.69211,0.55473,0.98365,0.60573,0.54224,0.57294,0.45987,0.73042,0.61601,0.99608,0.0007195,0.0007195,0.0007195
+87,35873.1,0.69119,0.55473,0.98453,0.62068,0.5373,0.57315,0.4601,0.73024,0.61575,0.99599,0.0007162,0.0007162,0.0007162
+88,36283.3,0.68924,0.55485,0.98278,0.6149,0.53637,0.57243,0.45938,0.73053,0.61529,0.99653,0.0007129,0.0007129,0.0007129
+89,36693.2,0.6881,0.54932,0.98155,0.61216,0.53666,0.57275,0.45942,0.73066,0.61513,0.99701,0.0007096,0.0007096,0.0007096
+90,37103.4,0.68748,0.54711,0.9811,0.61754,0.53869,0.57284,0.46038,0.73081,0.61537,0.99721,0.0007063,0.0007063,0.0007063
+91,37513.3,0.68639,0.54586,0.9802,0.61986,0.53636,0.573,0.46059,0.73082,0.61475,0.99741,0.000703,0.000703,0.000703
+92,37923.2,0.6858,0.54607,0.98105,0.6199,0.53775,0.57223,0.45978,0.73125,0.61554,0.99742,0.0006997,0.0006997,0.0006997
+93,38332.9,0.68458,0.5445,0.98017,0.62475,0.53637,0.57131,0.4599,0.73125,0.61601,0.99765,0.0006964,0.0006964,0.0006964
+94,38742.8,0.68476,0.54496,0.97901,0.62742,0.53615,0.57047,0.45943,0.73138,0.61591,0.99757,0.0006931,0.0006931,0.0006931
+95,39152.9,0.68467,0.54329,0.97949,0.62647,0.53598,0.56967,0.45891,0.73135,0.61586,0.99786,0.0006898,0.0006898,0.0006898
+96,39562.7,0.68248,0.53889,0.97827,0.63125,0.53332,0.56914,0.45883,0.73137,0.61569,0.99801,0.0006865,0.0006865,0.0006865
+97,39972.4,0.68149,0.53843,0.97811,0.63182,0.53225,0.56928,0.45931,0.73212,0.61574,0.99904,0.0006832,0.0006832,0.0006832
+98,40382.5,0.67966,0.53569,0.97732,0.63148,0.53334,0.56919,0.45914,0.73285,0.61689,1.0001,0.0006799,0.0006799,0.0006799
+99,40792.6,0.67831,0.53489,0.9763,0.63827,0.53174,0.56748,0.45676,0.7333,0.61708,1.00088,0.0006766,0.0006766,0.0006766
+100,41202.4,0.67859,0.53438,0.97539,0.64537,0.52882,0.56857,0.45781,0.73349,0.61774,1.00156,0.0006733,0.0006733,0.0006733
+101,41612,0.67698,0.53195,0.97421,0.59689,0.55476,0.56698,0.45707,0.73428,0.61818,1.0023,0.00067,0.00067,0.00067
+102,42021.9,0.67614,0.52984,0.97443,0.64668,0.52583,0.56655,0.4573,0.73411,0.61871,1.00209,0.0006667,0.0006667,0.0006667
+103,42431.9,0.67603,0.53043,0.97495,0.59965,0.5591,0.56899,0.45881,0.73429,0.61872,1.00227,0.0006634,0.0006634,0.0006634
+104,42842.1,0.67442,0.52656,0.97396,0.65822,0.5248,0.56951,0.45846,0.73465,0.61952,1.00245,0.0006601,0.0006601,0.0006601

fashion_yolo/fashionpedia_exp/yolov8m_fashion_final/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_reduced.yaml
+epochs: 500
+time: null
+patience: 50
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fashionpedia_exp
+name: yolov8m_fashion_final2
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fashion_yolo/fashionpedia_exp/yolov8m_fashion_final2

fashion_yolo/fashionpedia_exp/yolov8m_fashion_final/results.csv

@@ -0,0 +1,108 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,457.89,0.88683,1.32931,1.18557,0.51731,0.44505,0.44618,0.32256,0.95622,1.24877,1.19403,0.067034,0.00033299,0.00033299
+2,916.415,0.918,1.22373,1.19908,0.51802,0.45856,0.47624,0.35536,0.90873,1.08857,1.17258,0.0340327,0.000665004,0.000665004
+3,1375.07,0.89471,1.15842,1.18234,0.59881,0.49085,0.52052,0.39983,0.8716,0.98792,1.13218,0.00103003,0.000995698,0.000995698
+4,1829.35,0.84385,1.06735,1.15031,0.58293,0.5494,0.56973,0.44688,0.78717,0.86602,1.08828,0.00099406,0.00099406,0.00099406
+5,2280.57,0.80122,0.99233,1.12344,0.64024,0.58091,0.61291,0.49565,0.7324,0.78198,1.05296,0.00099208,0.00099208,0.00099208
+6,2732.37,0.77294,0.94658,1.10477,0.58446,0.61699,0.63157,0.51447,0.70957,0.73479,1.03662,0.0009901,0.0009901,0.0009901
+7,3183.72,0.75144,0.91401,1.09045,0.68525,0.61853,0.66465,0.54695,0.67567,0.69362,1.0173,0.00098812,0.00098812,0.00098812
+8,3634.19,0.73716,0.88066,1.08194,0.69799,0.63739,0.68292,0.56642,0.66128,0.66836,1.01048,0.00098614,0.00098614,0.00098614
+9,4085.8,0.72163,0.85649,1.07271,0.73886,0.62402,0.6918,0.57915,0.63789,0.64143,0.99556,0.00098416,0.00098416,0.00098416
+10,4537.19,0.7122,0.83631,1.06702,0.73234,0.65818,0.7105,0.59646,0.62256,0.61749,0.98779,0.00098218,0.00098218,0.00098218
+11,4988.92,0.69997,0.81747,1.05917,0.71541,0.66997,0.72246,0.61203,0.61202,0.60238,0.97674,0.0009802,0.0009802,0.0009802
+12,5440.49,0.69099,0.79945,1.05375,0.73632,0.67777,0.73404,0.62541,0.59816,0.58309,0.97069,0.00097822,0.00097822,0.00097822
+13,5892.2,0.68417,0.7835,1.05059,0.71903,0.68948,0.73839,0.6316,0.58965,0.57025,0.97066,0.00097624,0.00097624,0.00097624
+14,6343.54,0.67596,0.77427,1.04726,0.78736,0.66938,0.74799,0.64299,0.58801,0.56243,0.97139,0.00097426,0.00097426,0.00097426
+15,6794.76,0.67035,0.75674,1.04228,0.78497,0.6816,0.74962,0.64266,0.58505,0.55707,0.96724,0.00097228,0.00097228,0.00097228
+16,7245.86,0.66228,0.74541,1.03696,0.78396,0.6861,0.75294,0.64713,0.57994,0.55312,0.96355,0.0009703,0.0009703,0.0009703
+17,7697.5,0.65762,0.72954,1.03504,0.78443,0.69864,0.75598,0.65041,0.57789,0.54772,0.96355,0.00096832,0.00096832,0.00096832
+18,8148.76,0.65246,0.72311,1.03197,0.77804,0.71214,0.76245,0.65771,0.57606,0.54191,0.96332,0.00096634,0.00096634,0.00096634
+19,8599.95,0.64532,0.70783,1.02904,0.78333,0.71374,0.76433,0.65953,0.57378,0.53887,0.96165,0.00096436,0.00096436,0.00096436
+20,9051.33,0.64054,0.69728,1.02377,0.79915,0.70741,0.76972,0.66552,0.57205,0.53533,0.96076,0.00096238,0.00096238,0.00096238
+21,9502.62,0.63734,0.69125,1.02201,0.79518,0.71025,0.77018,0.66649,0.57049,0.53383,0.95993,0.0009604,0.0009604,0.0009604
+22,9953.79,0.63331,0.68273,1.02055,0.79763,0.71238,0.77075,0.66661,0.56907,0.53096,0.95902,0.00095842,0.00095842,0.00095842
+23,10405,0.62767,0.67424,1.0177,0.79869,0.71322,0.77373,0.66937,0.56745,0.52899,0.95812,0.00095644,0.00095644,0.00095644
+24,10856.2,0.62557,0.66267,1.01335,0.79272,0.71389,0.77391,0.66966,0.56675,0.52595,0.95704,0.00095446,0.00095446,0.00095446
+25,11307.8,0.6228,0.66036,1.01338,0.79825,0.7089,0.77352,0.66961,0.56559,0.52478,0.95629,0.00095248,0.00095248,0.00095248
+26,11759,0.61943,0.64768,1.00938,0.80146,0.70794,0.77467,0.67145,0.56379,0.52484,0.95511,0.0009505,0.0009505,0.0009505
+27,12209.9,0.61572,0.64537,1.00894,0.80189,0.70873,0.77538,0.67173,0.56254,0.52454,0.95405,0.00094852,0.00094852,0.00094852
+28,12661.1,0.6106,0.63838,1.00674,0.8059,0.69691,0.77772,0.67449,0.56148,0.52311,0.95344,0.00094654,0.00094654,0.00094654
+29,13112.4,0.61079,0.63358,1.00562,0.81364,0.6993,0.77911,0.67521,0.56085,0.52151,0.95275,0.00094456,0.00094456,0.00094456
+30,13563.4,0.60736,0.62771,1.0039,0.8167,0.70162,0.78063,0.67704,0.56021,0.51914,0.95196,0.00094258,0.00094258,0.00094258
+31,14014.7,0.60259,0.61985,0.9999,0.82663,0.69761,0.78214,0.67842,0.55884,0.51673,0.95085,0.0009406,0.0009406,0.0009406
+32,14465.7,0.60076,0.61614,0.9998,0.81385,0.70055,0.78048,0.67785,0.55743,0.51473,0.94952,0.00093862,0.00093862,0.00093862
+33,14916.9,0.59559,0.61001,0.9963,0.7904,0.72103,0.78147,0.67937,0.55604,0.5144,0.94898,0.00093664,0.00093664,0.00093664
+34,15368.1,0.59677,0.60432,0.99745,0.79309,0.72155,0.78511,0.681,0.55421,0.51439,0.94781,0.00093466,0.00093466,0.00093466
+35,15819,0.59436,0.59981,0.9958,0.78066,0.72799,0.78594,0.68171,0.55363,0.51403,0.94769,0.00093268,0.00093268,0.00093268
+36,16269.4,0.58839,0.5893,0.98983,0.83254,0.6988,0.78782,0.68435,0.55268,0.51254,0.94686,0.0009307,0.0009307,0.0009307
+37,16720.5,0.59039,0.59206,0.99453,0.83285,0.69858,0.79044,0.68656,0.55115,0.51143,0.94562,0.00092872,0.00092872,0.00092872
+38,17172.3,0.58499,0.58754,0.99226,0.83092,0.7069,0.79024,0.68596,0.54963,0.50939,0.94472,0.00092674,0.00092674,0.00092674
+39,17622.8,0.58285,0.58114,0.98975,0.83099,0.70834,0.78883,0.6843,0.54931,0.50774,0.94484,0.00092476,0.00092476,0.00092476
+40,18074,0.58215,0.57689,0.98926,0.8316,0.70731,0.78625,0.68251,0.54983,0.50725,0.9454,0.00092278,0.00092278,0.00092278
+41,18525,0.5798,0.57245,0.98881,0.82733,0.71305,0.78675,0.6837,0.5492,0.50711,0.94548,0.0009208,0.0009208,0.0009208
+42,18975.5,0.57903,0.56826,0.98735,0.83222,0.71435,0.78699,0.68425,0.54926,0.50586,0.94598,0.00091882,0.00091882,0.00091882
+43,19427,0.57443,0.56251,0.98391,0.83123,0.71496,0.78895,0.68475,0.54733,0.50456,0.9448,0.00091684,0.00091684,0.00091684
+44,19878.7,0.57384,0.55961,0.98381,0.83089,0.71451,0.78977,0.68517,0.54677,0.50361,0.94482,0.00091486,0.00091486,0.00091486
+45,20329.4,0.5729,0.55585,0.98206,0.82506,0.71059,0.79006,0.6856,0.54644,0.50347,0.94517,0.00091288,0.00091288,0.00091288
+46,20780.7,0.5705,0.5519,0.98273,0.82193,0.71212,0.7893,0.68622,0.54526,0.50296,0.94488,0.0009109,0.0009109,0.0009109
+47,21231.5,0.57039,0.54936,0.98328,0.81485,0.71467,0.78967,0.68573,0.54498,0.50265,0.94469,0.00090892,0.00090892,0.00090892
+48,21682.7,0.56927,0.54922,0.98108,0.80506,0.72397,0.79063,0.68688,0.54456,0.5021,0.94483,0.00090694,0.00090694,0.00090694
+49,22134.1,0.56478,0.54181,0.97904,0.79302,0.73117,0.78946,0.68703,0.54406,0.50194,0.94468,0.00090496,0.00090496,0.00090496
+50,22585.7,0.56338,0.53745,0.97706,0.77517,0.73775,0.78941,0.68732,0.54371,0.50229,0.9444,0.00090298,0.00090298,0.00090298
+51,23036.7,0.56128,0.53292,0.97478,0.80155,0.71624,0.78828,0.68467,0.54271,0.5022,0.94369,0.000901,0.000901,0.000901
+52,23487.8,0.56123,0.53205,0.97435,0.80061,0.71755,0.78773,0.68522,0.5422,0.50133,0.94338,0.00089902,0.00089902,0.00089902
+53,23938.2,0.55887,0.52587,0.97366,0.79307,0.71911,0.78783,0.68579,0.54101,0.50179,0.94267,0.00089704,0.00089704,0.00089704
+54,24389.2,0.5569,0.52658,0.97362,0.77412,0.72758,0.7872,0.68469,0.54015,0.5029,0.9424,0.00089506,0.00089506,0.00089506
+55,24840.5,0.55622,0.52079,0.97329,0.76262,0.74176,0.7893,0.68829,0.53902,0.50352,0.94193,0.00089308,0.00089308,0.00089308
+56,25291.9,0.55542,0.52175,0.97347,0.75164,0.75496,0.78918,0.68887,0.53851,0.50406,0.94191,0.0008911,0.0008911,0.0008911
+57,25742.9,0.5535,0.51809,0.97131,0.74686,0.75478,0.78671,0.68904,0.53857,0.50484,0.94218,0.00088912,0.00088912,0.00088912
+58,26194.2,0.55208,0.51515,0.97343,0.75846,0.74752,0.78558,0.68812,0.53858,0.5059,0.94267,0.00088714,0.00088714,0.00088714
+59,26645.4,0.55066,0.51327,0.97164,0.77666,0.72557,0.78524,0.68861,0.53804,0.50633,0.9427,0.00088516,0.00088516,0.00088516
+60,27096.8,0.54974,0.51001,0.9694,0.7264,0.77398,0.78355,0.68611,0.53658,0.50597,0.94206,0.00088318,0.00088318,0.00088318
+61,27548.1,0.54559,0.5052,0.96733,0.75503,0.75642,0.78355,0.68604,0.53534,0.50628,0.94114,0.0008812,0.0008812,0.0008812
+62,27999.4,0.54474,0.50356,0.96697,0.76073,0.75125,0.78297,0.68622,0.53525,0.50683,0.94149,0.00087922,0.00087922,0.00087922
+63,28450.5,0.54489,0.50109,0.96692,0.76253,0.74972,0.78137,0.68431,0.53442,0.50701,0.94117,0.00087724,0.00087724,0.00087724
+64,28901.9,0.54279,0.49894,0.96659,0.7633,0.74753,0.78198,0.68422,0.534,0.50808,0.94112,0.00087526,0.00087526,0.00087526
+65,29353.6,0.5446,0.49924,0.96593,0.76671,0.75031,0.78116,0.68332,0.53472,0.50707,0.94103,0.00087328,0.00087328,0.00087328
+66,29804.2,0.54173,0.49441,0.96263,0.76454,0.75281,0.78041,0.68392,0.53482,0.5069,0.94137,0.0008713,0.0008713,0.0008713
+67,30255.2,0.53911,0.49062,0.96278,0.76411,0.75269,0.78029,0.68218,0.53491,0.50599,0.94152,0.00086932,0.00086932,0.00086932
+68,30706.1,0.53856,0.48794,0.96289,0.76645,0.75188,0.78076,0.68253,0.53421,0.50596,0.94114,0.00086734,0.00086734,0.00086734
+69,31157.4,0.53968,0.48909,0.96455,0.76773,0.74754,0.78074,0.68375,0.53362,0.50555,0.94038,0.00086536,0.00086536,0.00086536
+70,31608.5,0.53628,0.48699,0.96154,0.77422,0.74093,0.77942,0.68391,0.53369,0.50468,0.94026,0.00086338,0.00086338,0.00086338
+71,32060.1,0.53537,0.48481,0.96135,0.78093,0.73938,0.77988,0.68439,0.53398,0.50439,0.94033,0.0008614,0.0008614,0.0008614
+72,32510.8,0.53519,0.48424,0.96144,0.77374,0.7459,0.78217,0.6873,0.53426,0.50416,0.94064,0.00085942,0.00085942,0.00085942
+73,32962,0.53448,0.48211,0.96052,0.76365,0.74936,0.78153,0.68739,0.53397,0.50588,0.94086,0.00085744,0.00085744,0.00085744
+74,33413.1,0.53141,0.47597,0.95823,0.76587,0.74857,0.7824,0.68773,0.53435,0.50584,0.94125,0.00085546,0.00085546,0.00085546
+75,33864.1,0.53026,0.47387,0.95857,0.77682,0.7289,0.78131,0.68765,0.53429,0.50494,0.94158,0.00085348,0.00085348,0.00085348
+76,34315,0.52914,0.4735,0.95905,0.77719,0.73672,0.78165,0.68694,0.534,0.50556,0.94164,0.0008515,0.0008515,0.0008515
+77,34766,0.53026,0.47048,0.95843,0.7549,0.75072,0.78287,0.68702,0.53376,0.50522,0.94169,0.00084952,0.00084952,0.00084952
+78,35216.7,0.52681,0.47115,0.95676,0.75612,0.7557,0.78295,0.68559,0.53249,0.50593,0.94083,0.00084754,0.00084754,0.00084754
+79,35667.8,0.52582,0.46752,0.95797,0.75908,0.7579,0.781,0.68412,0.53292,0.50724,0.94153,0.00084556,0.00084556,0.00084556
+80,36118.6,0.52694,0.46825,0.95616,0.749,0.7733,0.78172,0.68458,0.53265,0.50986,0.9416,0.00084358,0.00084358,0.00084358
+81,36570.1,0.52658,0.46707,0.95675,0.74576,0.76459,0.78112,0.68344,0.5338,0.51163,0.94245,0.0008416,0.0008416,0.0008416
+82,37021.7,0.52438,0.46259,0.95575,0.73804,0.78133,0.78056,0.68356,0.53479,0.51276,0.94353,0.00083962,0.00083962,0.00083962
+83,37473.3,0.5246,0.46244,0.95754,0.74546,0.77143,0.77955,0.68195,0.535,0.51347,0.94416,0.00083764,0.00083764,0.00083764
+84,37924.5,0.5228,0.45967,0.95448,0.7492,0.76876,0.77896,0.68264,0.53582,0.51257,0.94461,0.00083566,0.00083566,0.00083566
+85,38376,0.52085,0.45942,0.9541,0.74132,0.78106,0.77977,0.68229,0.5361,0.51318,0.94447,0.00083368,0.00083368,0.00083368
+86,38827.5,0.52124,0.45523,0.95424,0.73883,0.77121,0.78252,0.68506,0.53639,0.5152,0.94492,0.0008317,0.0008317,0.0008317
+87,39279.1,0.5171,0.45303,0.95061,0.76468,0.75787,0.7794,0.68039,0.53727,0.51576,0.9456,0.00082972,0.00082972,0.00082972
+88,39730.2,0.52005,0.45384,0.95344,0.76706,0.75256,0.77996,0.68002,0.53756,0.51479,0.94616,0.00082774,0.00082774,0.00082774
+89,40181.8,0.51805,0.45267,0.95219,0.76351,0.7541,0.78124,0.68107,0.53802,0.51426,0.94696,0.00082576,0.00082576,0.00082576
+90,40633.1,0.51703,0.45019,0.95272,0.73783,0.77513,0.78246,0.68086,0.53837,0.51332,0.94776,0.00082378,0.00082378,0.00082378
+91,41084.8,0.51559,0.44851,0.95219,0.81122,0.7152,0.78376,0.6829,0.5393,0.5135,0.94856,0.0008218,0.0008218,0.0008218
+92,41535.9,0.51465,0.44659,0.95235,0.807,0.71948,0.7853,0.68338,0.54013,0.51449,0.94903,0.00081982,0.00081982,0.00081982
+93,41986.8,0.51449,0.44483,0.95123,0.74369,0.77954,0.78389,0.68213,0.54058,0.51453,0.94929,0.00081784,0.00081784,0.00081784
+94,42438.8,0.51396,0.4426,0.94942,0.75636,0.77138,0.78564,0.68528,0.5398,0.51464,0.94925,0.00081586,0.00081586,0.00081586
+95,42889.9,0.51486,0.44344,0.95128,0.75353,0.76984,0.78619,0.68502,0.53954,0.51507,0.94948,0.00081388,0.00081388,0.00081388
+96,43341.1,0.51151,0.44189,0.94857,0.75198,0.77322,0.78581,0.68452,0.54018,0.5163,0.95016,0.0008119,0.0008119,0.0008119
+97,43792.6,0.50917,0.43834,0.94702,0.77034,0.75353,0.78541,0.68504,0.53944,0.51656,0.95005,0.00080992,0.00080992,0.00080992
+98,44243.9,0.51041,0.43968,0.94815,0.7627,0.76859,0.78607,0.68568,0.53983,0.51754,0.95151,0.00080794,0.00080794,0.00080794
+99,44695.2,0.50957,0.43676,0.94735,0.75896,0.76465,0.78632,0.68583,0.53844,0.51808,0.95059,0.00080596,0.00080596,0.00080596
+100,45146.3,0.50745,0.43537,0.94694,0.75391,0.77257,0.78599,0.68651,0.53775,0.51787,0.95023,0.00080398,0.00080398,0.00080398
+101,45597.5,0.50812,0.43582,0.94704,0.77745,0.75832,0.78675,0.68662,0.53684,0.51773,0.95023,0.000802,0.000802,0.000802
+102,46048.1,0.50562,0.43169,0.94502,0.78022,0.75828,0.78581,0.68707,0.53733,0.51798,0.95139,0.00080002,0.00080002,0.00080002
+103,46499.1,0.50575,0.43067,0.94398,0.75636,0.77235,0.7825,0.68496,0.5371,0.51874,0.95146,0.00079804,0.00079804,0.00079804
+104,46949.4,0.50372,0.42811,0.94322,0.76878,0.75628,0.78152,0.68417,0.53661,0.51882,0.95104,0.00079606,0.00079606,0.00079606
+105,47400.5,0.50518,0.4299,0.94321,0.80925,0.7268,0.78229,0.68461,0.5364,0.5197,0.95073,0.00079408,0.00079408,0.00079408
+106,47851.8,0.50258,0.42721,0.94219,0.77003,0.75321,0.78269,0.68599,0.5354,0.52134,0.94919,0.0007921,0.0007921,0.0007921
+107,48302.5,0.50185,0.4262,0.94187,0.77956,0.74669,0.78216,0.68629,0.53593,0.52174,0.94943,0.00079012,0.00079012,0.00079012

fashion_yolo/train.py

@@ -0,0 +1,33 @@
+from ultralytics import YOLO
+
+# 1. 모델 로드 (YOLOv8m 사용)
+model = YOLO('yolov8m.pt')
+
+# 2. 학습 실행
+# 위에서 생성된 yaml 파일 경로를 넣어줍니다.
+# train_results = model.train(
+#     data="/home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_custom_noface.yaml", 
+#     epochs=500,            
+#     imgsz=640,
+#     batch=-1,              
+#     device="cuda",
+#     optimizer='AdamW',
+#     lr0=0.001,
+#     patience=50,
+#     verbose=False,
+#     project='fashionpedia_exp',
+#     name='yolov8m_fashion_noface',
+# )
+
+train_results = model.train(
+    data="/home/cuuva/experiment/datasets/fashionpedia_yolo/fashionpedia_reduced.yaml", 
+    epochs=500,            
+    imgsz=640,
+    batch=-1,              
+    device="cuda",
+    optimizer='AdamW',
+    lr0=0.001,
+    patience=50,
+    project='fashionpedia_exp',
+    name='yolov8m_fashion_final',
+)

fire_smoke_detect/fire_detect/epo200_frac_0.2/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/fire_smoke_detect/fire_smoke_detect.yaml
+epochs: 200
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fire_detect
+name: epo200_frac_0.2
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 0.2
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.2

fire_smoke_detect/fire_detect/epo200_frac_0.2/results.csv

@@ -0,0 +1,25 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,1204.07,0.95333,0.88297,1.17171,0.58992,0.55779,0.52314,0.30558,1.48042,136.788,1.7476,0.0670152,0.00033318,0.00033318
+2,2383.91,0.79944,0.57825,1.07539,0.73966,0.5336,0.6041,0.36806,1.46003,38.3215,1.63618,0.0340119,0.000663214,0.000663214
+3,3566.65,0.75066,0.51917,1.0484,0.75522,0.58482,0.65317,0.41012,1.46256,44.4346,1.79015,0.00100533,0.000989948,0.000989948
+4,4735.57,0.7019,0.46977,1.02273,0.75449,0.63855,0.68668,0.4302,1.44598,44.1865,1.79038,0.00098515,0.00098515,0.00098515
+5,5859.2,0.66301,0.4336,1.00166,0.77177,0.62853,0.6912,0.44481,1.44808,25.727,1.82837,0.0009802,0.0009802,0.0009802
+6,6968.48,0.63622,0.40996,0.98828,0.77734,0.61917,0.68599,0.44422,1.46789,18.762,1.85945,0.00097525,0.00097525,0.00097525
+7,8081.49,0.61699,0.39367,0.97882,0.77549,0.62608,0.69685,0.45085,1.48469,20.1125,1.89911,0.0009703,0.0009703,0.0009703
+8,9220.8,0.60255,0.38103,0.97085,0.78339,0.62475,0.69614,0.45177,1.49066,17.4359,1.9208,0.00096535,0.00096535,0.00096535
+9,10376.2,0.59013,0.37139,0.96545,0.78828,0.62522,0.69971,0.45559,1.49618,15.4245,1.93214,0.0009604,0.0009604,0.0009604
+10,11515.2,0.58102,0.36325,0.96117,0.79348,0.61961,0.70075,0.45759,1.51214,13.5958,1.95824,0.00095545,0.00095545,0.00095545
+11,12674.1,0.57188,0.35542,0.9561,0.79279,0.61913,0.70323,0.46097,1.52172,11.9689,1.98155,0.0009505,0.0009505,0.0009505
+12,13823.3,0.56364,0.34945,0.9517,0.80111,0.61334,0.70511,0.46359,1.53195,10.5718,2.00195,0.00094555,0.00094555,0.00094555
+13,14995.6,0.55753,0.34407,0.94937,0.80248,0.61197,0.70717,0.46689,1.5384,9.1532,2.01451,0.0009406,0.0009406,0.0009406
+14,16151.8,0.55225,0.33933,0.94648,0.79867,0.61024,0.70813,0.46864,1.54897,8.68019,2.04261,0.00093565,0.00093565,0.00093565
+15,17275.9,0.54685,0.33535,0.9443,0.80185,0.60429,0.70758,0.46968,1.54495,8.10419,2.05172,0.0009307,0.0009307,0.0009307
+16,18394.7,0.54267,0.33146,0.94234,0.80234,0.60287,0.70742,0.4705,1.55287,7.80516,2.07675,0.00092575,0.00092575,0.00092575
+17,19541,0.53647,0.32675,0.93905,0.80107,0.60273,0.70643,0.47033,1.56068,8.17225,2.09467,0.0009208,0.0009208,0.0009208
+18,20666.8,0.53343,0.3251,0.93774,0.79937,0.60026,0.70523,0.47066,1.55671,8.13241,2.0926,0.00091585,0.00091585,0.00091585
+19,21805.2,0.52936,0.32165,0.9363,0.80178,0.59748,0.70382,0.47064,1.55926,8.47417,2.10418,0.0009109,0.0009109,0.0009109
+20,22964,0.52662,0.31932,0.93506,0.80164,0.59668,0.70238,0.4695,1.56229,8.74841,2.10729,0.00090595,0.00090595,0.00090595
+21,24118.8,0.52338,0.3163,0.93373,0.80306,0.59725,0.70186,0.46896,1.57132,9.11794,2.12589,0.000901,0.000901,0.000901
+22,25255.9,0.52038,0.31379,0.93242,0.80596,0.5975,0.70275,0.4691,1.57325,9.34025,2.14093,0.00089605,0.00089605,0.00089605
+23,26383.7,0.51748,0.3118,0.93098,0.8063,0.59731,0.70253,0.46937,1.56901,9.38138,2.13283,0.0008911,0.0008911,0.0008911
+24,27530.6,0.51485,0.31016,0.92922,0.80466,0.5979,0.70179,0.46895,1.57327,9.19169,2.14732,0.00088615,0.00088615,0.00088615

fire_smoke_detect/fire_detect/epo200_frac_0.22/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/fire_smoke_detect/fire_smoke_detect.yaml
+epochs: 200
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fire_detect
+name: epo200_frac_0.22
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 0.2
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.22

fire_smoke_detect/fire_detect/epo200_frac_0.22/results.csv

@@ -0,0 +1,2 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,1222.25,0.95333,0.88297,1.17171,0.58992,0.55779,0.52314,0.30558,1.48042,136.788,1.7476,0.0670152,0.00033318,0.00033318

fire_smoke_detect/fire_detect/epo200_frac_0.23/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/fire_smoke_detect/fire_smoke_detect.yaml
+epochs: 200
+time: null
+patience: 30
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fire_detect
+name: epo200_frac_0.23
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 0.2
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23

fire_smoke_detect/fire_detect/epo200_frac_0.23/results.csv

@@ -0,0 +1,49 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,1231.29,0.95333,0.88297,1.17171,0.58992,0.55779,0.52314,0.30558,1.48042,136.788,1.7476,0.0670152,0.00033318,0.00033318
+2,2305.09,0.79944,0.57825,1.07539,0.73966,0.5336,0.6041,0.36806,1.46003,38.3215,1.63618,0.0340119,0.000663214,0.000663214
+3,3266.85,0.75066,0.51917,1.0484,0.75522,0.58482,0.65317,0.41012,1.46256,44.4346,1.79015,0.00100533,0.000989948,0.000989948
+4,4223.68,0.7019,0.46977,1.02273,0.75449,0.63855,0.68668,0.4302,1.44598,44.1865,1.79038,0.00098515,0.00098515,0.00098515
+5,5164.86,0.66301,0.4336,1.00166,0.77177,0.62853,0.6912,0.44481,1.44808,25.727,1.82837,0.0009802,0.0009802,0.0009802
+6,6107.2,0.63622,0.40996,0.98828,0.77734,0.61917,0.68599,0.44422,1.46789,18.762,1.85945,0.00097525,0.00097525,0.00097525
+7,7044.13,0.61699,0.39367,0.97882,0.77549,0.62608,0.69685,0.45085,1.48469,20.1125,1.89911,0.0009703,0.0009703,0.0009703
+8,7986.66,0.60255,0.38103,0.97085,0.78339,0.62475,0.69614,0.45177,1.49066,17.4359,1.9208,0.00096535,0.00096535,0.00096535
+9,8921.81,0.59013,0.37139,0.96545,0.78828,0.62522,0.69971,0.45559,1.49618,15.4245,1.93214,0.0009604,0.0009604,0.0009604
+10,9846.06,0.58102,0.36325,0.96117,0.79348,0.61961,0.70075,0.45759,1.51214,13.5958,1.95824,0.00095545,0.00095545,0.00095545
+11,10771.6,0.57188,0.35542,0.9561,0.79279,0.61913,0.70323,0.46097,1.52172,11.9689,1.98155,0.0009505,0.0009505,0.0009505
+12,11690.6,0.56364,0.34945,0.9517,0.80111,0.61334,0.70511,0.46359,1.53195,10.5718,2.00195,0.00094555,0.00094555,0.00094555
+13,12610.4,0.55753,0.34407,0.94937,0.80248,0.61197,0.70717,0.46689,1.5384,9.1532,2.01451,0.0009406,0.0009406,0.0009406
+14,13530.7,0.55225,0.33933,0.94648,0.79867,0.61024,0.70813,0.46864,1.54897,8.68019,2.04261,0.00093565,0.00093565,0.00093565
+15,14450.7,0.54685,0.33535,0.9443,0.80185,0.60429,0.70758,0.46968,1.54495,8.10419,2.05172,0.0009307,0.0009307,0.0009307
+16,15368.8,0.54267,0.33146,0.94234,0.80234,0.60287,0.70742,0.4705,1.55287,7.80516,2.07675,0.00092575,0.00092575,0.00092575
+17,16304.6,0.53647,0.32675,0.93905,0.80107,0.60273,0.70643,0.47033,1.56068,8.17225,2.09467,0.0009208,0.0009208,0.0009208
+18,17249.5,0.53343,0.3251,0.93774,0.79937,0.60026,0.70523,0.47066,1.55671,8.13241,2.0926,0.00091585,0.00091585,0.00091585
+19,18197.8,0.52936,0.32165,0.9363,0.80178,0.59748,0.70382,0.47064,1.55926,8.47417,2.10418,0.0009109,0.0009109,0.0009109
+20,19143.1,0.52662,0.31932,0.93506,0.80164,0.59668,0.70238,0.4695,1.56229,8.74841,2.10729,0.00090595,0.00090595,0.00090595
+21,20080.6,0.52338,0.3163,0.93373,0.80306,0.59725,0.70186,0.46896,1.57132,9.11794,2.12589,0.000901,0.000901,0.000901
+22,21026.9,0.52038,0.31379,0.93242,0.80596,0.5975,0.70275,0.4691,1.57325,9.34025,2.14093,0.00089605,0.00089605,0.00089605
+23,21973.4,0.51748,0.3118,0.93098,0.8063,0.59731,0.70253,0.46937,1.56901,9.38138,2.13283,0.0008911,0.0008911,0.0008911
+24,22909.7,0.51485,0.31016,0.92922,0.80466,0.5979,0.70179,0.46895,1.57327,9.19169,2.14732,0.00088615,0.00088615,0.00088615
+25,23850.8,inf,0.30745,0.92818,0.80276,0.59834,0.70088,0.46777,1.57743,9.46807,2.16309,0.0008812,0.0008812,0.0008812
+26,24790.1,inf,0.30615,0.92772,0.80289,0.59767,0.70073,0.46684,1.57848,9.53053,2.16149,0.00087625,0.00087625,0.00087625
+27,25726.8,0.5076,0.30424,0.92655,0.80403,0.59709,0.7002,0.46536,1.57713,10.1806,2.16274,0.0008713,0.0008713,0.0008713
+28,26661.7,0.50585,0.30305,0.92576,0.80228,0.5971,0.6998,0.46502,1.57733,10.1693,2.1652,0.00086635,0.00086635,0.00086635
+29,27599.4,0.50306,0.30056,0.92434,0.80314,0.59518,0.69922,0.46453,1.58016,9.98943,2.17888,0.0008614,0.0008614,0.0008614
+30,28538.5,0.50155,0.29911,0.92367,0.8028,0.59304,0.69757,0.46292,1.58332,10.546,2.18906,0.00085645,0.00085645,0.00085645
+31,29477.3,0.49893,0.29753,0.9224,0.80206,0.59255,0.69616,0.46183,1.58237,11.1724,2.1932,0.0008515,0.0008515,0.0008515
+32,30419.6,0.49697,0.29575,0.92136,0.80252,0.59236,0.69581,0.46209,1.58474,11.3598,2.19785,0.00084655,0.00084655,0.00084655
+33,31345.4,0.49527,0.2948,0.92082,0.80121,0.59174,0.6951,0.46091,1.58227,12.4389,2.19247,0.0008416,0.0008416,0.0008416
+34,32280.3,0.49344,0.29327,0.91958,0.8004,0.59011,0.6945,0.45992,1.58068,12.9417,2.1865,0.00083665,0.00083665,0.00083665
+35,33212.5,0.49199,0.29225,0.91942,0.79787,0.5911,0.69395,0.45908,1.57832,13.358,2.1876,0.0008317,0.0008317,0.0008317
+36,34147.6,0.49082,0.2914,0.91864,0.79629,0.59203,0.69372,0.45872,1.58015,13.725,2.19326,0.00082675,0.00082675,0.00082675
+37,35079.1,0.48962,0.29024,0.9183,0.79505,0.59202,0.69331,0.45841,1.58044,14.7538,2.20086,0.0008218,0.0008218,0.0008218
+38,36002.2,0.48822,0.28901,0.9174,0.7924,0.59201,0.69178,0.45807,1.5832,14.9679,2.20654,0.00081685,0.00081685,0.00081685
+39,36936.4,0.48609,0.28799,0.91666,0.78931,0.59349,0.69133,0.45783,1.58224,15.523,2.2005,0.0008119,0.0008119,0.0008119
+40,37873.4,0.48492,0.28646,0.91595,0.78576,0.59477,0.69122,0.45733,1.57714,15.8603,2.18981,0.00080695,0.00080695,0.00080695
+41,38809.6,0.48358,0.28569,0.91544,0.78608,0.594,0.69158,0.45675,1.58096,16.1674,2.1928,0.000802,0.000802,0.000802
+42,39745.5,0.48262,0.28443,0.91611,0.78173,0.59728,0.69192,0.45633,1.58189,16.9209,2.20177,0.00079705,0.00079705,0.00079705
+43,40675,0.48087,0.28369,0.91546,0.78293,0.59837,0.69231,0.45555,1.58687,17.469,2.2154,0.0007921,0.0007921,0.0007921
+44,41612.1,0.47984,0.28248,0.91398,0.78191,0.59908,0.69255,0.45503,1.58852,16.9581,2.22694,0.00078715,0.00078715,0.00078715
+45,42561.8,inf,0.28182,0.91365,0.78538,0.59734,0.69201,0.45388,1.59065,17.8763,2.23381,0.0007822,0.0007822,0.0007822
+46,43500.5,0.47734,0.28076,0.91301,0.78908,0.59446,0.69184,0.454,1.59332,17.9766,2.24166,0.00077725,0.00077725,0.00077725
+47,44444.4,0.47562,0.28004,0.9127,0.78747,0.59572,0.69197,0.4531,1.59389,18.2731,2.24922,0.0007723,0.0007723,0.0007723
+48,45385.8,0.47473,0.27879,0.91198,0.78282,0.59854,0.69222,0.45333,1.59942,18.0307,2.25994,0.00076735,0.00076735,0.00076735

fire_smoke_detect/fire_detect/test/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/fire_smoke_detect/fire_smoke_detect.yaml
+epochs: 3
+time: null
+patience: 2
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: fire_detect
+name: test
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 0.2
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/fire_smoke_detect/fire_detect/test

fire_smoke_detect/fire_detect/test/results.csv

@@ -0,0 +1,4 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,1199.61,0.95333,0.88297,1.17171,0.58992,0.55779,0.52314,0.30558,1.48042,136.788,1.7476,0.0670152,0.00033318,0.00033318
+2,2232.52,0.76985,0.54965,1.05934,0.72812,0.57948,0.63698,0.39352,1.45385,49.7197,1.71483,0.0337953,0.000446564,0.000446564
+3,3210.1,0.68091,0.45689,1.01277,0.77079,0.60657,0.6896,0.43966,1.37136,36.4624,1.57494,0.00035533,0.000339948,0.000339948

fire_smoke_detect/fire_exp.ipynb

@@ -0,0 +1,820 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a7676704",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from ultralytics import YOLO\n",
+    "\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3e94066a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "torch.cuda.is_available()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "99b0442c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "New https://pypi.org/project/ultralytics/8.3.227 available 😃 Update with 'pip install -U ultralytics'\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.8.0+cu129 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, augment=False, auto_augment=randaugment, batch=-1, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=/home/cuuva/experiment/fire_smoke_detect/fire_smoke_detect.yaml, degrees=0.0, deterministic=True, device=0, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, epochs=200, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=0.2, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.001, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolov8n.pt, momentum=0.937, mosaic=1.0, multi_scale=False, name=epo200_frac_0.23, nbs=64, nms=False, opset=None, optimize=False, optimizer=AdamW, overlap_mask=True, patience=30, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=fire_detect, rect=False, resume=False, retina_masks=False, save=True, save_conf=False, save_crop=False, save_dir=/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n",
+      "Overriding model.yaml nc=80 with nc=2\n",
+      "\n",
+      "                   from  n    params  module                                       arguments                     \n",
+      "  0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]                 \n",
+      "  1                  -1  1      4672  ultralytics.nn.modules.conv.Conv             [16, 32, 3, 2]                \n",
+      "  2                  -1  1      7360  ultralytics.nn.modules.block.C2f             [32, 32, 1, True]             \n",
+      "  3                  -1  1     18560  ultralytics.nn.modules.conv.Conv             [32, 64, 3, 2]                \n",
+      "  4                  -1  2     49664  ultralytics.nn.modules.block.C2f             [64, 64, 2, True]             \n",
+      "  5                  -1  1     73984  ultralytics.nn.modules.conv.Conv             [64, 128, 3, 2]               \n",
+      "  6                  -1  2    197632  ultralytics.nn.modules.block.C2f             [128, 128, 2, True]           \n",
+      "  7                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]              \n",
+      "  8                  -1  1    460288  ultralytics.nn.modules.block.C2f             [256, 256, 1, True]           \n",
+      "  9                  -1  1    164608  ultralytics.nn.modules.block.SPPF            [256, 256, 5]                 \n",
+      " 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 12                  -1  1    148224  ultralytics.nn.modules.block.C2f             [384, 128, 1]                 \n",
+      " 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 15                  -1  1     37248  ultralytics.nn.modules.block.C2f             [192, 64, 1]                  \n",
+      " 16                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]                \n",
+      " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 18                  -1  1    123648  ultralytics.nn.modules.block.C2f             [192, 128, 1]                 \n",
+      " 19                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]              \n",
+      " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 21                  -1  1    493056  ultralytics.nn.modules.block.C2f             [384, 256, 1]                 \n",
+      " 22        [15, 18, 21]  1    751702  ultralytics.nn.modules.head.Detect           [2, [64, 128, 256]]           \n",
+      "Model summary: 129 layers, 3,011,238 parameters, 3,011,222 gradients, 8.2 GFLOPs\n",
+      "\n",
+      "Transferred 319/355 items from pretrained weights\n",
+      "Freezing layer 'model.22.dfl.conv.weight'\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 708.3±281.4 MB/s, size: 334.0 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/aihub_car/fire_dataset/Training/labels/FL/ENB/0174/JPG.cache... 305424 images, 1715 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 305424/305424 572.9Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mComputing optimal batch size for imgsz=640 at 60.0% CUDA memory utilization.\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mCUDA:0 (NVIDIA GeForce RTX 5090) 31.33G total, 0.15G reserved, 0.05G allocated, 31.13G free\n",
+      "      Params      GFLOPs  GPU_mem (GB)  forward (ms) backward (ms)                   input                  output\n",
+      "     3011238       8.195         3.450         35.09         227.5        (1, 3, 640, 640)                    list\n",
+      "     3011238       16.39         3.991         4.973         24.53        (2, 3, 640, 640)                    list\n",
+      "     3011238       32.78         4.261         5.241         24.53        (4, 3, 640, 640)                    list\n",
+      "     3011238       65.56         4.970          5.51         30.21        (8, 3, 640, 640)                    list\n",
+      "     3011238       131.1         6.117         7.798         40.44       (16, 3, 640, 640)                    list\n",
+      "     3011238       262.2         4.855         15.02            54       (32, 3, 640, 640)                    list\n",
+      "     3011238       524.5        10.557         30.83         104.5       (64, 3, 640, 640)                    list\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mUsing batch-size 141 for CUDA:0 19.15G/31.33G (61%) ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 704.0±204.4 MB/s, size: 445.0 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/aihub_car/fire_dataset/Training/labels/FL/ENB/0174/JPG.cache... 305424 images, 1715 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 305424/305424 593.6Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 825.4±75.3 MB/s, size: 500.0 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /home/cuuva/aihub_car/fire_dataset/Validation/labels/FL/ENB/0953/JPG.cache... 190800 images, 38386 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 190800/190800 255.3Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00001.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00002.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00003.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00004.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00005.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00006.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00007.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00008.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00009.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00010.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00011.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00012.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00013.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00014.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00015.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00016.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00017.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00018.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00019.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00020.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00021.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00022.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00023.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00024.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00025.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00026.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00027.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00028.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00029.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00030.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00031.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00032.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00033.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00034.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00035.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00036.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00037.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00038.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00039.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00040.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00041.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00042.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00043.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00044.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00045.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00046.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00047.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00048.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00049.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00050.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00051.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00052.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00053.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00054.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00055.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00056.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00057.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00058.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00059.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00060.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00061.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00062.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00063.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00064.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00065.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00066.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00067.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00068.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00069.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00070.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00071.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00072.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00073.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00074.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00075.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00076.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00077.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00078.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00079.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00080.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00081.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00082.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00083.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00084.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00085.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00086.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00087.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00088.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00089.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00090.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00091.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00092.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00093.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00094.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00095.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00096.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00097.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00098.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00099.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00100.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00101.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00102.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00103.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00104.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00105.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00106.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00107.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00108.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00109.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00110.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00111.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00112.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00113.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00114.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00115.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00116.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00117.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00118.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00119.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00120.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00121.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00122.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00123.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00124.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00125.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00126.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00127.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00128.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00129.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00130.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00131.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00132.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00133.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00134.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00135.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00136.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00137.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00138.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00139.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00140.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00141.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00142.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00143.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00144.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00145.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00146.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00147.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00148.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00149.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00150.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00151.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00152.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00153.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00154.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00155.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00156.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00157.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00158.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00159.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00160.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00161.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00162.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00163.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00164.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00165.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00166.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00167.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00168.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00169.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00170.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00171.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00172.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00173.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00174.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00175.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00176.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00177.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00178.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00179.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00180.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00181.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00182.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00183.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00184.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00185.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00186.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00187.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00188.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00189.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00190.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00191.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00192.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00193.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00194.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00195.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00196.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00197.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00198.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00199.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00200.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00201.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00202.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00203.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00204.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00205.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00206.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00207.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00208.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00209.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00210.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00211.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00212.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00213.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00214.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00215.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00216.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00217.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00218.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00219.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00220.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00221.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00222.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00223.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00224.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00225.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00226.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00227.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00228.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00229.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00230.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00231.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00232.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00233.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00234.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00235.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00236.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00237.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00238.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00239.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00240.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00241.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00242.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00243.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00244.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00245.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00246.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00247.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00248.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00249.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00250.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00251.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00252.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00253.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00254.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00255.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00256.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00257.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00258.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00259.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00260.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00261.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00262.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00263.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00264.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00265.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00266.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00267.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00268.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00269.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00270.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00271.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00272.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00273.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00274.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00275.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00276.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00277.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00278.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00279.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00280.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00281.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00282.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00283.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00284.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00285.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00286.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00287.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00288.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00289.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00290.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00291.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00292.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00293.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00294.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00295.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00296.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00297.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00298.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00299.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00300.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00301.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00302.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00303.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00304.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00305.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00306.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00307.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00308.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00309.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00310.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00311.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00312.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00313.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00314.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00315.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00316.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00317.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00318.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00319.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00320.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00321.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00322.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00323.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00324.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00325.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00326.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00327.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00328.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00329.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00330.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00331.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00332.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00333.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00334.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00335.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00336.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00337.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00338.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00339.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00340.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00341.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00342.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00343.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00344.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00345.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00346.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00347.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00348.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00349.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00350.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00351.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00352.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00353.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00354.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00355.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00356.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00357.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00358.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00359.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mval: \u001b[0m/home/cuuva/aihub_car/fire_dataset/Validation/images/FL/MS/2317/JPG/2317_FL_MS_00360.jpg: 1 duplicate labels removed\n",
+      "Plotting labels to /home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/labels.jpg... \n",
+      "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.001, momentum=0.937) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0011015625000000001), 63 bias(decay=0.0)\n",
+      "Image sizes 640 train, 640 val\n",
+      "Using 8 dataloader workers\n",
+      "Logging results to \u001b[1m/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23\u001b[0m\n",
+      "Starting training for 200 epochs...\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      1/200      18.7G     0.9533      0.883      1.172         60        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:03<0.2s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.0it/s 2:47<0.2s\n",
+      "                   all     190800     194206       0.59      0.558      0.523      0.306\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      2/200      18.7G     0.7994     0.5782      1.075         66        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:49<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.3it/s 2:39<0.2s\n",
+      "                   all     190800     194206       0.74      0.534      0.604      0.368\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      3/200      18.7G     0.7507     0.5192      1.048         60        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:48<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.3it/s 2:36<0.2s\n",
+      "                   all     190800     194206      0.755      0.585      0.653       0.41\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      4/200      18.7G     0.7019     0.4698      1.023         43        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:47<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.4it/s 2:35<0.2s\n",
+      "                   all     190800     194206      0.754      0.639      0.687       0.43\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      5/200      18.7G      0.663     0.4336      1.002         70        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:45<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.4it/s 2:33<0.2s\n",
+      "                   all     190800     194206      0.772      0.629      0.691      0.445\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      6/200      18.7G     0.6362       0.41     0.9883         53        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:48<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.4it/s 2:33<0.2s\n",
+      "                   all     190800     194206      0.777      0.619      0.686      0.444\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      7/200      18.7G      0.617     0.3937     0.9788         60        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:46<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:31<0.2s\n",
+      "                   all     190800     194206      0.775      0.626      0.697      0.451\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      8/200      18.7G     0.6026      0.381     0.9708         62        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:51<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.2s\n",
+      "                   all     190800     194206      0.783      0.625      0.696      0.452\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      9/200      18.7G     0.5901     0.3714     0.9654         58        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:51<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.2s\n",
+      "                   all     190800     194206      0.788      0.625        0.7      0.456\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     10/200      18.7G      0.581     0.3632     0.9612         57        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:47<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.793       0.62      0.701      0.458\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     11/200      18.7G     0.5719     0.3554     0.9561         58        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:50<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.2s\n",
+      "                   all     190800     194206      0.793      0.619      0.703      0.461\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     12/200      18.7G     0.5636     0.3495     0.9517         58        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:45<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.801      0.613      0.705      0.464\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     13/200      18.7G     0.5575     0.3441     0.9494         66        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:46<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:26<0.3s\n",
+      "                   all     190800     194206      0.802      0.612      0.707      0.467\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     14/200      18.7G     0.5523     0.3393     0.9465         57        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:50<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:27<0.2s\n",
+      "                   all     190800     194206      0.799       0.61      0.708      0.469\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     15/200      18.7G     0.5468     0.3353     0.9443         73        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:48<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:26<0.2s\n",
+      "                   all     190800     194206      0.802      0.604      0.708       0.47\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     16/200      18.7G     0.5427     0.3315     0.9423         69        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:48<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:26<0.2s\n",
+      "                   all     190800     194206      0.802      0.603      0.707      0.471\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     17/200      18.7G     0.5365     0.3268      0.939         66        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:58<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.4it/s 2:35<0.2s\n",
+      "                   all     190800     194206      0.801      0.603      0.706       0.47\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     18/200      18.7G     0.5334     0.3251     0.9377         65        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:08<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.2s\n",
+      "                   all     190800     194206      0.799        0.6      0.705      0.471\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     19/200      18.7G     0.5294     0.3216     0.9363         54        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:10<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.4it/s 2:34<0.3s\n",
+      "                   all     190800     194206      0.802      0.597      0.704      0.471\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     20/200      18.7G     0.5266     0.3193     0.9351         55        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:10<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.802      0.597      0.702      0.469\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     21/200      18.7G     0.5234     0.3163     0.9337         55        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:05<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:27<0.2s\n",
+      "                   all     190800     194206      0.803      0.597      0.702      0.469\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     22/200      18.7G     0.5204     0.3138     0.9324         67        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:11<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.3s\n",
+      "                   all     190800     194206      0.806      0.598      0.703      0.469\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     23/200      18.7G     0.5175     0.3118      0.931         68        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:14<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.2s\n",
+      "                   all     190800     194206      0.806      0.597      0.703      0.469\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     24/200      18.7G     0.5149     0.3102     0.9292         56        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:05<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.3s\n",
+      "                   all     190800     194206      0.805      0.598      0.702      0.469\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     25/200      18.7G        inf     0.3075     0.9282         54        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:10<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.803      0.598      0.701      0.468\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     26/200      18.7G        inf     0.3061     0.9277         63        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:08<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.3s\n",
+      "                   all     190800     194206      0.803      0.598      0.701      0.467\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     27/200      18.7G     0.5076     0.3042     0.9265         46        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:03<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.804      0.597        0.7      0.465\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     28/200      18.7G     0.5059     0.3031     0.9258         71        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:02<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.802      0.597        0.7      0.465\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     29/200      18.7G     0.5031     0.3006     0.9243         58        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:06<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.803      0.595      0.699      0.465\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     30/200      18.7G     0.5015     0.2991     0.9237         63        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:07<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:27<0.2s\n",
+      "                   all     190800     194206      0.803      0.593      0.698      0.463\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     31/200      18.7G     0.4989     0.2975     0.9224         66        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:04<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.802      0.593      0.696      0.462\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     32/200      18.7G      0.497     0.2958     0.9214         65        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:09<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:27<0.2s\n",
+      "                   all     190800     194206      0.803      0.592      0.696      0.462\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     33/200      18.7G     0.4953     0.2948     0.9208         42        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:55<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:27<0.2s\n",
+      "                   all     190800     194206      0.801      0.592      0.695      0.461\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     34/200      18.7G     0.4934     0.2933     0.9196         60        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:01<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:29<0.2s\n",
+      "                   all     190800     194206        0.8       0.59      0.694       0.46\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     35/200      18.7G      0.492     0.2922     0.9194         54        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:00<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.798      0.591      0.694      0.459\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     36/200      18.7G     0.4908     0.2914     0.9186         58        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:04<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.796      0.592      0.694      0.459\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     37/200      18.7G     0.4896     0.2902     0.9183         51        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:57<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.3s\n",
+      "                   all     190800     194206      0.795      0.592      0.693      0.458\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     38/200      18.7G     0.4882      0.289     0.9174         64        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:53<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.792      0.592      0.692      0.458\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     39/200      18.7G     0.4861      0.288     0.9167         50        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:58<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.789      0.593      0.691      0.458\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     40/200      18.7G     0.4849     0.2865      0.916         70        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:03<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.786      0.595      0.691      0.457\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     41/200      18.7G     0.4836     0.2857     0.9154         59        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:05<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.786      0.594      0.692      0.457\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     42/200      18.7G     0.4826     0.2844     0.9161         81        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:59<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.3s\n",
+      "                   all     190800     194206      0.782      0.597      0.692      0.456\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     43/200      18.7G     0.4809     0.2837     0.9155         58        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 12:56<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.783      0.598      0.692      0.456\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     44/200      18.7G     0.4798     0.2825      0.914         62        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:04<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.782      0.599      0.693      0.455\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     45/200      18.7G        inf     0.2818     0.9137         70        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:16<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:31<0.2s\n",
+      "                   all     190800     194206      0.785      0.597      0.692      0.454\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     46/200      18.7G     0.4773     0.2808      0.913         70        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:05<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:29<0.2s\n",
+      "                   all     190800     194206      0.789      0.594      0.692      0.454\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     47/200      18.7G     0.4756       0.28     0.9127         57        640: 100% ━━━━━━━━━━━━ 2167/2167 2.7it/s 13:10<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.6it/s 2:28<0.2s\n",
+      "                   all     190800     194206      0.787      0.596      0.692      0.453\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     48/200      18.7G     0.4747     0.2788      0.912         62        640: 100% ━━━━━━━━━━━━ 2167/2167 2.8it/s 13:07<0.7s\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.5it/s 2:30<0.2s\n",
+      "                   all     190800     194206      0.783      0.599      0.692      0.453\n",
+      "\u001b[34m\u001b[1mEarlyStopping: \u001b[0mTraining stopped early as no improvement observed in last 30 epochs. Best results observed at epoch 18, best model saved as best.pt.\n",
+      "To update EarlyStopping(patience=30) pass a new patience value, i.e. `patience=300` or use `patience=0` to disable EarlyStopping.\n",
+      "\n",
+      "48 epochs completed in 12.607 hours.\n",
+      "Optimizer stripped from /home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/last.pt, 6.2MB\n",
+      "Optimizer stripped from /home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.pt, 6.2MB\n",
+      "\n",
+      "Validating /home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.pt...\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.8.0+cu129 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "Model summary (fused): 72 layers, 3,006,038 parameters, 0 gradients, 8.1 GFLOPs\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 677/677 4.0it/s 2:50<0.3s\n",
+      "                   all     190800     194206        0.8      0.601      0.705      0.471\n",
+      "                 flame      72076      75235      0.819      0.759      0.837      0.605\n",
+      "                 smoke     116127     118971      0.781      0.443      0.574      0.336\n",
+      "Speed: 0.0ms preprocess, 0.2ms inference, 0.0ms loss, 0.2ms postprocess per image\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load a pretrained YOLO11n model\n",
+    "model = YOLO(\"yolov8n.pt\")\n",
+    "\n",
+    "train_results = model.train(\n",
+    "    data=\"/home/cuuva/experiment/fire_smoke_detect/fire_smoke_detect.yaml\",\n",
+    "    epochs=200,\n",
+    "    imgsz=640,\n",
+    "    batch=-1,\n",
+    "    device=\"cuda\",\n",
+    "    optimizer = 'AdamW',\n",
+    "    lr0 = 0.001,\n",
+    "    patience = 30,\n",
+    "    project = 'fire_detect',\n",
+    "    name = 'epo200_frac_0.2',\n",
+    "    fraction = 0.2\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "88d6a47e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.8.0+cu129 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model summary (fused): 72 layers, 3,006,038 parameters, 0 gradients, 8.1 GFLOPs\n",
+      "\n",
+      "\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from '/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 6, 8400) (5.9 MB)\n",
+      "\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m starting export with onnx 1.19.1 opset 20...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m slimming with onnxslim 0.1.71...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m export success ✅ 2.9s, saved as '/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.onnx' (11.7 MB)\n",
+      "\n",
+      "Export complete (3.0s)\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights\u001b[0m\n",
+      "Predict:         yolo predict task=detect model=/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.onnx imgsz=640  \n",
+      "Validate:        yolo val task=detect model=/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.onnx imgsz=640 data=/home/cuuva/experiment/fire_smoke_detect/fire_smoke_detect.yaml  \n",
+      "Visualize:       https://netron.app\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.onnx'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = YOLO(\"/home/cuuva/experiment/fire_smoke_detect/fire_detect/epo200_frac_0.23/weights/best.pt\")\n",
+    "model.export(format=\"onnx\", imgsz=640, device=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7ad3f495",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "1stagedetect",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

fire_smoke_detect/fire_smoke_detect.yaml

@@ -0,0 +1,10 @@
+# 데이터셋 경로
+train: /home/cuuva/aihub_car/fire_dataset/Training/images/
+val: /home/cuuva/aihub_car/fire_dataset/Validation/images/
+
+# 클래스 수
+nc: 2
+
+# 클래스 이름
+names: ['flame', 'smoke']
+

swoon_detect/sw_detect/final_100epoch/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8n.pt
+data: /home/cuuva/experiment/swoon_detect/swoon_detect.yaml
+epochs: 300
+time: null
+patience: 50
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: sw_detect
+name: final_100epoch
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/swoon_detect/sw_detect/final_100epoch

swoon_detect/sw_detect/final_100epoch/results.csv

@@ -0,0 +1,132 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,34.7021,0.99692,3.11052,0.95462,0,0,0,0,1.96969,5.09543,1.66347,0.07624,0.00024,0.00024
+2,58.1564,0.88533,0.81005,0.95966,0,0,0,0,1.13737,5.66392,1.11577,0.0514884,0.000488383,0.000488383
+3,92.7895,0.83799,0.71399,0.94176,0.61429,0.46655,0.55241,0.41655,0.98618,4.08179,1.04621,0.0267351,0.000735116,0.000735116
+4,105.051,0.79628,0.66035,0.92157,0.81025,0.49367,0.6697,0.38789,1.35581,2.29532,1.21563,0.0019802,0.000980199,0.000980199
+5,129.478,0.81136,0.63385,0.94036,0.90182,0.76404,0.81811,0.543,1.13814,0.99886,1.19084,0.0009868,0.0009868,0.0009868
+6,141.623,0.77441,0.59174,0.92343,0.79664,0.72963,0.70525,0.45371,1.09478,1.06992,1.22257,0.0009835,0.0009835,0.0009835
+7,154.902,0.77167,0.57802,0.91993,0.8682,0.83183,0.86792,0.63549,0.83551,0.70814,0.9794,0.0009802,0.0009802,0.0009802
+8,169.038,0.74894,0.55503,0.91538,0.819,0.76492,0.80273,0.54722,0.98313,0.94247,1.06882,0.0009769,0.0009769,0.0009769
+9,181.969,0.72558,0.5317,0.90209,0.87925,0.8481,0.8802,0.66413,0.84099,0.61761,0.99128,0.0009736,0.0009736,0.0009736
+10,195.299,0.7306,0.51875,0.91204,0.8461,0.82098,0.84278,0.60296,0.8736,0.70076,1.05043,0.0009703,0.0009703,0.0009703
+11,206.919,0.71221,0.52812,0.90491,0.89736,0.85714,0.89136,0.66282,0.8198,0.87756,0.98645,0.000967,0.000967,0.000967
+12,217.7,0.68637,0.49626,0.89712,0.89841,0.83363,0.8516,0.6221,0.8753,0.73016,1.09195,0.0009637,0.0009637,0.0009637
+13,228.845,0.66379,0.47568,0.8969,0.87593,0.84259,0.82557,0.58133,0.86205,0.68953,1.09495,0.0009604,0.0009604,0.0009604
+14,239.297,0.68917,0.49114,0.89622,0.87716,0.86511,0.86626,0.63591,0.81925,0.61207,1.06045,0.0009571,0.0009571,0.0009571
+15,250.335,0.67633,0.47741,0.89762,0.89996,0.83183,0.86878,0.63899,0.75256,0.64579,0.96647,0.0009538,0.0009538,0.0009538
+16,261.353,0.63476,0.46476,0.8834,0.88932,0.87182,0.88096,0.66666,0.77169,0.5558,1.01473,0.0009505,0.0009505,0.0009505
+17,272.608,0.65515,0.46115,0.88384,0.8921,0.83363,0.86032,0.62239,0.83968,0.87876,1.07603,0.0009472,0.0009472,0.0009472
+18,284.717,0.64001,0.45228,0.87949,0.88447,0.81555,0.85197,0.63428,0.82735,0.59532,1.03181,0.0009439,0.0009439,0.0009439
+19,296.522,0.62268,0.4525,0.88487,0.91193,0.84262,0.88032,0.64832,0.79121,0.61895,1.03754,0.0009406,0.0009406,0.0009406
+20,309.592,0.63448,0.44433,0.88512,0.87666,0.82261,0.81656,0.55511,0.95443,0.65184,1.22882,0.0009373,0.0009373,0.0009373
+21,322.182,0.63823,0.44304,0.88037,0.89522,0.85172,0.86106,0.60464,0.86042,0.51554,1.10164,0.000934,0.000934,0.000934
+22,336.13,0.6077,0.4324,0.8729,0.89107,0.85714,0.84127,0.61986,0.81008,0.57466,1.06811,0.0009307,0.0009307,0.0009307
+23,350.28,0.6207,0.43229,0.87345,0.9104,0.83183,0.8714,0.6628,0.78211,0.51027,1.03652,0.0009274,0.0009274,0.0009274
+24,363.862,0.61806,0.43114,0.87883,0.88748,0.8415,0.87401,0.64248,0.81787,0.49065,1.08271,0.0009241,0.0009241,0.0009241
+25,377.203,0.61985,0.43001,0.87774,0.90222,0.83183,0.87338,0.6879,0.68979,1.01589,0.94388,0.0009208,0.0009208,0.0009208
+26,390.499,0.61656,0.42297,0.87265,0.93582,0.86799,0.9013,0.67935,0.76562,0.49424,0.98975,0.0009175,0.0009175,0.0009175
+27,400.903,0.59142,0.40623,0.86666,0.92075,0.84629,0.88782,0.65838,0.77885,0.49803,1.04222,0.0009142,0.0009142,0.0009142
+28,410.675,0.61042,0.41839,0.86873,0.90809,0.86257,0.87778,0.6555,0.76453,0.49995,1.00262,0.0009109,0.0009109,0.0009109
+29,420.742,0.60576,0.41804,0.87656,0.91377,0.86235,0.88164,0.6601,0.73928,0.50308,0.99722,0.0009076,0.0009076,0.0009076
+30,430.739,0.60603,0.41587,0.87676,0.89383,0.85254,0.89738,0.70005,0.71229,0.57312,0.94632,0.0009043,0.0009043,0.0009043
+31,441.256,0.58791,0.41053,0.8654,0.90738,0.86618,0.88465,0.66675,0.76349,0.49064,1.0192,0.000901,0.000901,0.000901
+32,451.956,0.58351,0.401,0.86283,0.91953,0.88854,0.90063,0.67086,0.78939,0.45019,1.0224,0.0008977,0.0008977,0.0008977
+33,462.051,0.58838,0.41156,0.86788,0.92141,0.848,0.9108,0.69488,0.76778,0.49542,0.97043,0.0008944,0.0008944,0.0008944
+34,472.298,0.5913,0.4086,0.8747,0.91674,0.85612,0.88607,0.64755,0.76797,0.52436,1.02984,0.0008911,0.0008911,0.0008911
+35,484.125,0.57349,0.40808,0.865,0.90827,0.84156,0.88382,0.65875,0.76037,0.52884,1.00972,0.0008878,0.0008878,0.0008878
+36,500.707,0.57406,0.39802,0.86615,0.90859,0.86618,0.89931,0.67024,0.76235,0.47401,1.03001,0.0008845,0.0008845,0.0008845
+37,516.541,0.5699,0.39999,0.8673,0.90577,0.8698,0.87365,0.62141,0.80525,0.53512,1.10353,0.0008812,0.0008812,0.0008812
+38,532.623,0.54216,0.38326,0.85993,0.9205,0.87936,0.9027,0.68621,0.76165,0.46101,1.01179,0.0008779,0.0008779,0.0008779
+39,543.733,0.5696,0.40019,0.86481,0.92391,0.87834,0.90979,0.70101,0.72586,0.44776,0.99587,0.0008746,0.0008746,0.0008746
+40,558.525,0.56581,0.39388,0.8605,0.90462,0.87469,0.90686,0.7134,0.70046,0.43642,0.9893,0.0008713,0.0008713,0.0008713
+41,571.17,0.56399,0.38437,0.86165,0.91521,0.88608,0.90844,0.70078,0.68867,0.45458,0.96522,0.000868,0.000868,0.000868
+42,584.833,0.56076,0.39028,0.85887,0.90656,0.88608,0.91085,0.7337,0.70138,0.42411,0.95804,0.0008647,0.0008647,0.0008647
+43,598.723,0.54489,0.38042,0.85394,0.90197,0.86618,0.89149,0.68332,0.75302,0.47361,1.01357,0.0008614,0.0008614,0.0008614
+44,611.639,0.55044,0.37233,0.85598,0.93751,0.87884,0.9118,0.72068,0.68576,0.43353,0.95107,0.0008581,0.0008581,0.0008581
+45,624.771,0.55095,0.37455,0.85631,0.90754,0.85199,0.87837,0.68771,0.70368,0.4779,0.9985,0.0008548,0.0008548,0.0008548
+46,640.54,0.56156,0.38495,0.86831,0.90819,0.85859,0.87414,0.64421,0.77426,0.45845,1.048,0.0008515,0.0008515,0.0008515
+47,655.686,0.5547,0.37727,0.85514,0.91334,0.87665,0.90121,0.68988,0.76153,0.45147,1.04075,0.0008482,0.0008482,0.0008482
+48,669.206,0.56647,0.38913,0.86151,0.90202,0.88427,0.89978,0.66623,0.76016,0.46199,1.03915,0.0008449,0.0008449,0.0008449
+49,684.126,0.53937,0.36699,0.85849,0.89649,0.8457,0.89009,0.67258,0.77955,0.45769,1.07779,0.0008416,0.0008416,0.0008416
+50,698.461,0.54831,0.36492,0.85622,0.89782,0.88065,0.90287,0.71383,0.697,0.42852,1.00059,0.0008383,0.0008383,0.0008383
+51,713.645,0.54613,0.36397,0.85931,0.90096,0.87703,0.88793,0.67727,0.75559,0.47143,1.01223,0.000835,0.000835,0.000835
+52,731.977,0.54465,0.37022,0.86009,0.90715,0.88338,0.89602,0.68439,0.7357,0.4338,1.01677,0.0008317,0.0008317,0.0008317
+53,743.045,0.52914,0.37523,0.8544,0.89495,0.88246,0.90087,0.69102,0.73401,0.46935,1.00157,0.0008284,0.0008284,0.0008284
+54,754.526,0.52389,0.36796,0.85348,0.90375,0.87703,0.90136,0.68208,0.72443,0.4251,0.99654,0.0008251,0.0008251,0.0008251
+55,766.145,0.53695,0.37007,0.8593,0.92242,0.88065,0.90644,0.69544,0.72786,0.43352,1.01616,0.0008218,0.0008218,0.0008218
+56,777.738,0.53298,0.37268,0.85449,0.92986,0.87884,0.91812,0.70779,0.72376,0.4199,1.02072,0.0008185,0.0008185,0.0008185
+57,789.079,0.52278,0.36385,0.84482,0.93893,0.86187,0.90375,0.69383,0.70366,0.44424,0.99126,0.0008152,0.0008152,0.0008152
+58,800.046,0.53586,0.36782,0.8521,0.93618,0.85172,0.88593,0.6846,0.72546,0.48908,1.02899,0.0008119,0.0008119,0.0008119
+59,812.447,0.51175,0.3556,0.84435,0.91532,0.87955,0.89698,0.66439,0.78617,0.44624,1.08033,0.0008086,0.0008086,0.0008086
+60,822.502,0.52929,0.35839,0.8547,0.91753,0.88788,0.90612,0.67992,0.7899,0.43338,1.04613,0.0008053,0.0008053,0.0008053
+61,835.085,0.53648,0.36334,0.85282,0.94742,0.88427,0.92062,0.70481,0.72008,0.4443,0.96516,0.000802,0.000802,0.000802
+62,846.861,0.51907,0.35473,0.84629,0.92732,0.87703,0.89766,0.68322,0.70787,0.47261,1.01025,0.0007987,0.0007987,0.0007987
+63,858.564,0.51051,0.3523,0.85127,0.92886,0.88427,0.90168,0.70173,0.69482,0.46427,0.97892,0.0007954,0.0007954,0.0007954
+64,870.064,0.52071,0.3634,0.85274,0.92049,0.8698,0.88206,0.68041,0.71646,0.48517,1.00591,0.0007921,0.0007921,0.0007921
+65,882.799,0.50793,0.34813,0.85074,0.9073,0.88065,0.90013,0.69868,0.70316,0.45048,0.98568,0.0007888,0.0007888,0.0007888
+66,896.029,0.51142,0.34745,0.8548,0.90485,0.85353,0.89757,0.69137,0.73512,0.42862,1.05296,0.0007855,0.0007855,0.0007855
+67,907.816,0.51635,0.34536,0.85241,0.92261,0.88388,0.90844,0.7153,0.67732,0.41922,1.00051,0.0007822,0.0007822,0.0007822
+68,918.958,0.50808,0.35686,0.84852,0.94178,0.86257,0.90453,0.66669,0.76668,0.43723,1.07557,0.0007789,0.0007789,0.0007789
+69,931.244,0.4998,0.33677,0.84352,0.92619,0.88496,0.90317,0.68321,0.75844,0.42174,1.04478,0.0007756,0.0007756,0.0007756
+70,942.872,0.52196,0.35231,0.8499,0.92503,0.87021,0.90893,0.69302,0.72319,0.45712,1.01505,0.0007723,0.0007723,0.0007723
+71,955.449,0.50125,0.33892,0.84865,0.91341,0.87752,0.90688,0.69514,0.723,0.41792,1.03109,0.000769,0.000769,0.000769
+72,968.156,0.49979,0.34101,0.84551,0.93439,0.89331,0.9212,0.72195,0.69226,0.40073,0.97614,0.0007657,0.0007657,0.0007657
+73,980.354,0.51371,0.34288,0.84347,0.93253,0.87475,0.89787,0.69665,0.71931,0.41821,0.99889,0.0007624,0.0007624,0.0007624
+74,991.234,0.50302,0.33922,0.84588,0.90984,0.87342,0.90602,0.69639,0.7558,0.42219,1.05959,0.0007591,0.0007591,0.0007591
+75,1004.05,0.49584,0.34472,0.84401,0.92344,0.86438,0.8959,0.68855,0.72366,0.43524,1.02242,0.0007558,0.0007558,0.0007558
+76,1014.82,0.49028,0.33776,0.84343,0.92713,0.89725,0.91799,0.70346,0.7291,0.41195,1.01147,0.0007525,0.0007525,0.0007525
+77,1027.12,0.49405,0.32601,0.84625,0.92347,0.89467,0.90552,0.69395,0.72762,0.41947,1.04666,0.0007492,0.0007492,0.0007492
+78,1039.23,0.49736,0.33638,0.84642,0.92874,0.87703,0.91351,0.69864,0.70537,0.42223,1.02199,0.0007459,0.0007459,0.0007459
+79,1051,0.49819,0.34083,0.84315,0.89828,0.88969,0.91238,0.69457,0.72477,0.42391,1.02981,0.0007426,0.0007426,0.0007426
+80,1066.14,0.51095,0.3441,0.85009,0.87679,0.87703,0.87828,0.65401,0.76728,0.49605,1.10681,0.0007393,0.0007393,0.0007393
+81,1079.16,0.50392,0.3406,0.84965,0.91518,0.87161,0.91496,0.74287,0.65844,0.3773,0.98431,0.000736,0.000736,0.000736
+82,1090.51,0.50999,0.33647,0.84333,0.92449,0.88065,0.91303,0.72863,0.64829,0.40398,0.97032,0.0007327,0.0007327,0.0007327
+83,1103.58,0.48732,0.33154,0.84668,0.90863,0.88114,0.89377,0.69624,0.71363,0.42001,1.02309,0.0007294,0.0007294,0.0007294
+84,1115,0.5065,0.33619,0.84501,0.9053,0.90778,0.91101,0.69981,0.71369,0.39276,1.01418,0.0007261,0.0007261,0.0007261
+85,1128.82,0.48695,0.32756,0.83675,0.92652,0.88427,0.91005,0.71521,0.66321,0.41992,0.9582,0.0007228,0.0007228,0.0007228
+86,1140.24,0.48709,0.32554,0.83767,0.90453,0.85663,0.89772,0.68684,0.7045,0.51257,1.01486,0.0007195,0.0007195,0.0007195
+87,1151.85,0.48991,0.33384,0.84448,0.907,0.85895,0.89311,0.7048,0.688,0.40654,1.02405,0.0007162,0.0007162,0.0007162
+88,1165.82,0.47768,0.32078,0.84114,0.91335,0.87703,0.90457,0.71941,0.69662,0.41756,1.01658,0.0007129,0.0007129,0.0007129
+89,1179.9,0.46292,0.31346,0.83747,0.92017,0.87523,0.90512,0.70031,0.70133,0.41296,1.01517,0.0007096,0.0007096,0.0007096
+90,1191.64,0.47472,0.32031,0.8383,0.94056,0.85172,0.91256,0.69874,0.74546,0.43067,1.03178,0.0007063,0.0007063,0.0007063
+91,1203.66,0.47272,0.31834,0.83749,0.95372,0.86799,0.91379,0.72971,0.65447,0.40239,0.98918,0.000703,0.000703,0.000703
+92,1216.18,0.47563,0.32345,0.83923,0.93656,0.85353,0.90677,0.71197,0.68924,0.39718,1.0055,0.0006997,0.0006997,0.0006997
+93,1227.95,0.46929,0.31942,0.8356,0.90919,0.86907,0.88844,0.68078,0.71498,0.4308,1.03819,0.0006964,0.0006964,0.0006964
+94,1240.14,0.47526,0.32685,0.84088,0.9424,0.85533,0.90051,0.69235,0.719,0.46186,1.00832,0.0006931,0.0006931,0.0006931
+95,1252.74,0.48414,0.32903,0.84224,0.92802,0.83933,0.89681,0.70984,0.71585,0.42711,0.99938,0.0006898,0.0006898,0.0006898
+96,1265.32,0.47906,0.3228,0.84473,0.90319,0.86043,0.91377,0.71846,0.73123,0.42424,1.02599,0.0006865,0.0006865,0.0006865
+97,1280.87,0.48515,0.32743,0.84377,0.92493,0.89127,0.91324,0.70149,0.68474,0.42236,1.00245,0.0006832,0.0006832,0.0006832
+98,1297.05,0.47635,0.31794,0.84276,0.95706,0.88608,0.92523,0.70832,0.72985,0.38181,1.0252,0.0006799,0.0006799,0.0006799
+99,1310.21,0.48074,0.3315,0.83991,0.93131,0.87342,0.91162,0.69733,0.73048,0.39416,1.04901,0.0006766,0.0006766,0.0006766
+100,1324.04,0.4728,0.31981,0.8406,0.90226,0.86804,0.89342,0.69261,0.71012,0.40061,1.03366,0.0006733,0.0006733,0.0006733
+101,1337.56,0.47076,0.31483,0.83844,0.91424,0.85353,0.90281,0.712,0.69518,0.41087,1.01541,0.00067,0.00067,0.00067
+102,1349.55,0.46218,0.32041,0.8428,0.92492,0.84655,0.89672,0.69095,0.71203,0.41839,1.03681,0.0006667,0.0006667,0.0006667
+103,1361.88,0.47578,0.32417,0.84119,0.9111,0.8698,0.8834,0.66869,0.72213,0.44994,1.06049,0.0006634,0.0006634,0.0006634
+104,1373.19,0.44611,0.3066,0.83246,0.91481,0.86257,0.88833,0.6986,0.69694,0.41254,1.05253,0.0006601,0.0006601,0.0006601
+105,1386.37,0.46857,0.3156,0.83695,0.92071,0.86092,0.89771,0.71171,0.67548,0.38121,1.03343,0.0006568,0.0006568,0.0006568
+106,1398.46,0.45919,0.30846,0.83651,0.91555,0.86076,0.90131,0.70325,0.7458,0.40659,1.08415,0.0006535,0.0006535,0.0006535
+107,1411.68,0.45874,0.3063,0.83803,0.90968,0.8924,0.91799,0.71584,0.69706,0.38962,1.00431,0.0006502,0.0006502,0.0006502
+108,1424.53,0.4754,0.31973,0.84394,0.92331,0.87703,0.89881,0.67953,0.73075,0.41059,1.05216,0.0006469,0.0006469,0.0006469
+109,1438.7,0.46546,0.31341,0.83591,0.92759,0.87884,0.90256,0.71366,0.69365,0.39958,0.992,0.0006436,0.0006436,0.0006436
+110,1452.06,0.45854,0.31392,0.84118,0.93255,0.87502,0.91568,0.70022,0.72925,0.41023,1.00777,0.0006403,0.0006403,0.0006403
+111,1465.5,0.44592,0.30402,0.82915,0.94543,0.88427,0.90657,0.70177,0.7009,0.3977,1.0271,0.000637,0.000637,0.000637
+112,1477.06,0.45529,0.31071,0.83851,0.9054,0.87161,0.8999,0.69202,0.7317,0.40164,1.04734,0.0006337,0.0006337,0.0006337
+113,1488.71,0.46451,0.31103,0.83599,0.91115,0.87884,0.90566,0.70506,0.73948,0.37495,1.05174,0.0006304,0.0006304,0.0006304
+114,1500.81,0.46996,0.31577,0.83512,0.9083,0.87342,0.89372,0.68722,0.74065,0.42079,1.06653,0.0006271,0.0006271,0.0006271
+115,1513.38,0.45662,0.31001,0.83788,0.91057,0.8698,0.88247,0.68998,0.70139,0.40224,1.0493,0.0006238,0.0006238,0.0006238
+116,1524.08,0.45388,0.31186,0.83535,0.91681,0.87342,0.89354,0.72169,0.66688,0.40111,0.97052,0.0006205,0.0006205,0.0006205
+117,1536.61,0.45111,0.30597,0.83164,0.93357,0.88948,0.91159,0.69986,0.71294,0.39073,1.02112,0.0006172,0.0006172,0.0006172
+118,1549.47,0.4345,0.2954,0.82631,0.9232,0.87161,0.89594,0.69382,0.70477,0.40546,1.03334,0.0006139,0.0006139,0.0006139
+119,1562.12,0.44801,0.30341,0.83352,0.91578,0.86512,0.89412,0.70999,0.69146,0.43679,1.00766,0.0006106,0.0006106,0.0006106
+120,1573.48,0.46259,0.31746,0.84003,0.94086,0.86303,0.91118,0.71194,0.69432,0.40778,1.00319,0.0006073,0.0006073,0.0006073
+121,1586.94,0.45296,0.31182,0.83985,0.93357,0.88946,0.90923,0.68917,0.71741,0.39807,1.06493,0.000604,0.000604,0.000604
+122,1599.18,0.45678,0.30899,0.83971,0.92137,0.88788,0.90705,0.73081,0.65972,0.39474,0.96801,0.0006007,0.0006007,0.0006007
+123,1612.03,0.4371,0.29534,0.829,0.93054,0.87161,0.89555,0.70609,0.68901,0.40615,1.02068,0.0005974,0.0005974,0.0005974
+124,1623.18,0.44696,0.30177,0.82855,0.89859,0.88131,0.90181,0.69312,0.70231,0.40449,1.03315,0.0005941,0.0005941,0.0005941
+125,1635.74,0.42877,0.29038,0.82506,0.92344,0.87241,0.89231,0.68589,0.71746,0.42029,1.054,0.0005908,0.0005908,0.0005908
+126,1646.86,0.43511,0.29468,0.82365,0.92015,0.87703,0.90056,0.67951,0.72235,0.42416,1.05745,0.0005875,0.0005875,0.0005875
+127,1659.88,0.43624,0.29691,0.833,0.93942,0.87703,0.91105,0.72035,0.67245,0.40004,1.0088,0.0005842,0.0005842,0.0005842
+128,1673.21,0.44243,0.29824,0.83473,0.91167,0.89331,0.9076,0.70523,0.71986,0.39723,1.02448,0.0005809,0.0005809,0.0005809
+129,1684.86,0.44449,0.30788,0.8389,0.92457,0.88969,0.90368,0.70112,0.68756,0.41945,1.01377,0.0005776,0.0005776,0.0005776
+130,1698.56,0.43999,0.30379,0.83098,0.92088,0.8915,0.90796,0.70892,0.67524,0.39043,1.01174,0.0005743,0.0005743,0.0005743
+131,1711.07,0.43848,0.29905,0.82695,0.92732,0.87679,0.89832,0.69459,0.69666,0.40026,1.04369,0.000571,0.000571,0.000571

swoon_detect/swoon_detect.yaml

@@ -0,0 +1,10 @@
+# 데이터셋 경로
+train: /home/cuuva/experiment/datasets/swoon_detection/Training/images/
+val: /home/cuuva/experiment/datasets/swoon_detection/Validation/images/
+
+# 클래스 수
+nc: 1
+
+# 클래스 이름
+names: ['swoon']
+

ultralytics

@@ -0,0 +1 @@
+Subproject commit 25738f5195fb98021521e733f406208ed494ffa3

vis5class_exp/vis5class.yaml

@@ -0,0 +1,9 @@
+# path: /home/cuuva/experiment/datasets/VisDrone  # 데이터 경로
+train: /home/cuuva/experiment/datasets/vis5class/images/train
+val: /home/cuuva/experiment/datasets/vis5class/images/val
+test: /home/cuuva/experiment/datasets/vis5class/images/test
+
+# nc: 7
+nc: 5
+
+names: ['person','car', 'truck', 'bus', 'motor']

vis5class_exp/vis5class_exp.ipynb

@@ -0,0 +1,955 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6b410dab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from ultralytics import YOLO\n",
+    "\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f66929b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "torch.cuda.is_available()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e5e2ab7b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "🔍 Checking split: train  (files: 6471)\n",
+      "\n",
+      "🔍 Checking split: val  (files: 548)\n",
+      "\n",
+      "🔍 Checking split: test  (files: 1610)\n",
+      "\n",
+      "📌 클래스 통계 결과:\n",
+      " - Class 0: 147747 개\n",
+      " - Class 1: 219707 개\n",
+      " - Class 2: 16284 개\n",
+      " - Class 3: 9117 개\n",
+      " - Class 4: 40378 개\n",
+      "\n",
+      "총 클래스 종류: 5\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from collections import Counter\n",
+    "\n",
+    "label_root = \"/home/cuuva/experiment/datasets/vis5class/labels\"\n",
+    "splits = [\"train\", \"val\", \"test\"]\n",
+    "\n",
+    "class_counter = Counter()\n",
+    "\n",
+    "for split in splits:\n",
+    "    split_path = os.path.join(label_root, split)\n",
+    "    \n",
+    "    # 라벨 txt 파일 탐색\n",
+    "    label_files = [f for f in os.listdir(split_path) if f.endswith(\".txt\")]\n",
+    "    \n",
+    "    print(f\"\\n🔍 Checking split: {split}  (files: {len(label_files)})\")\n",
+    "\n",
+    "    for file in label_files:\n",
+    "        file_path = os.path.join(split_path, file)\n",
+    "        with open(file_path, \"r\") as f:\n",
+    "            for line in f.readlines():\n",
+    "                if line.strip():  # 빈 줄 제거\n",
+    "                    class_id = line.split()[0]  # 첫번째 값 = 클래스\n",
+    "                    class_counter[class_id] += 1\n",
+    "\n",
+    "# 최종 결과 출력\n",
+    "print(\"\\n📌 클래스 통계 결과:\")\n",
+    "for cls, count in sorted(class_counter.items(), key=lambda x: int(x[0])):\n",
+    "    print(f\" - Class {cls}: {count} 개\")\n",
+    "\n",
+    "print(f\"\\n총 클래스 종류: {len(class_counter)}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6bb38c03",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[KDownloading https://github.com/ultralytics/assets/releases/download/v8.3.0/yolov8m.pt to 'yolov8m.pt': 100% ━━━━━━━━━━━━ 49.7MB 70.1MB/s 0.7s0.7s<0.0s\n",
+      "New https://pypi.org/project/ultralytics/8.3.234 available 😃 Update with 'pip install -U ultralytics'\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, augment=False, auto_augment=randaugment, batch=-1, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=/home/cuuva/experiment/vis5class_exp/vis5class.yaml, degrees=0.0, deterministic=True, device=0, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, epochs=300, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.001, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolov8m.pt, momentum=0.937, mosaic=1.0, multi_scale=False, name=5class, nbs=64, nms=False, opset=None, optimize=False, optimizer=AdamW, overlap_mask=True, patience=40, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=vis5class_v8m, rect=False, resume=False, retina_masks=False, save=True, save_conf=False, save_crop=False, save_dir=/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n",
+      "Overriding model.yaml nc=80 with nc=5\n",
+      "\n",
+      "                   from  n    params  module                                       arguments                     \n",
+      "  0                  -1  1      1392  ultralytics.nn.modules.conv.Conv             [3, 48, 3, 2]                 \n",
+      "  1                  -1  1     41664  ultralytics.nn.modules.conv.Conv             [48, 96, 3, 2]                \n",
+      "  2                  -1  2    111360  ultralytics.nn.modules.block.C2f             [96, 96, 2, True]             \n",
+      "  3                  -1  1    166272  ultralytics.nn.modules.conv.Conv             [96, 192, 3, 2]               \n",
+      "  4                  -1  4    813312  ultralytics.nn.modules.block.C2f             [192, 192, 4, True]           \n",
+      "  5                  -1  1    664320  ultralytics.nn.modules.conv.Conv             [192, 384, 3, 2]              \n",
+      "  6                  -1  4   3248640  ultralytics.nn.modules.block.C2f             [384, 384, 4, True]           \n",
+      "  7                  -1  1   1991808  ultralytics.nn.modules.conv.Conv             [384, 576, 3, 2]              \n",
+      "  8                  -1  2   3985920  ultralytics.nn.modules.block.C2f             [576, 576, 2, True]           \n",
+      "  9                  -1  1    831168  ultralytics.nn.modules.block.SPPF            [576, 576, 5]                 \n",
+      " 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 12                  -1  2   1993728  ultralytics.nn.modules.block.C2f             [960, 384, 2]                 \n",
+      " 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 15                  -1  2    517632  ultralytics.nn.modules.block.C2f             [576, 192, 2]                 \n",
+      " 16                  -1  1    332160  ultralytics.nn.modules.conv.Conv             [192, 192, 3, 2]              \n",
+      " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 18                  -1  2   1846272  ultralytics.nn.modules.block.C2f             [576, 384, 2]                 \n",
+      " 19                  -1  1   1327872  ultralytics.nn.modules.conv.Conv             [384, 384, 3, 2]              \n",
+      " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 21                  -1  2   4207104  ultralytics.nn.modules.block.C2f             [960, 576, 2]                 \n",
+      " 22        [15, 18, 21]  1   3778591  ultralytics.nn.modules.head.Detect           [5, [192, 384, 576]]          \n",
+      "Model summary: 169 layers, 25,859,215 parameters, 25,859,199 gradients, 79.1 GFLOPs\n",
+      "\n",
+      "Transferred 469/475 items from pretrained weights\n",
+      "Freezing layer 'model.22.dfl.conv.weight'\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n",
+      "\u001b[KDownloading https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt to 'yolo11n.pt': 100% ━━━━━━━━━━━━ 5.4MB 73.7MB/s 0.1s\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 12140.0±4222.1 MB/s, size: 260.7 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/experiment/datasets/vis5class/labels/train... 6471 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 6471/6471 5.3Kit/s 1.2s0.0s\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/0000137_02220_d_0000163.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/0000140_00118_d_0000002.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999945_00000_d_0000114.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999972_00000_d_0000158.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999981_00000_d_0000047.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999987_00000_d_0000049.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /home/cuuva/experiment/datasets/vis5class/labels/train.cache\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mComputing optimal batch size for imgsz=640 at 60.0% CUDA memory utilization.\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mCUDA:0 (NVIDIA GeForce RTX 5090) 31.33G total, 0.25G reserved, 0.24G allocated, 30.85G free\n",
+      "      Params      GFLOPs  GPU_mem (GB)  forward (ms) backward (ms)                   input                  output\n",
+      "    25859215       79.08         2.382         28.74         146.3        (1, 3, 640, 640)                    list\n",
+      "    25859215       158.2         3.811         9.848         33.63        (2, 3, 640, 640)                    list\n",
+      "    25859215       316.3         5.216         13.39         46.45        (4, 3, 640, 640)                    list\n",
+      "    25859215       632.6         8.735         26.08         69.81        (8, 3, 640, 640)                    list\n",
+      "    25859215        1265        12.298         27.03         116.4       (16, 3, 640, 640)                    list\n",
+      "    25859215        2531        24.285         54.71         238.4       (32, 3, 640, 640)                    list\n",
+      "    25859215        5061        28.001         116.9         470.2       (64, 3, 640, 640)                    list\n",
+      "\u001b[34m\u001b[1mAutoBatch: \u001b[0mUsing batch-size 34 for CUDA:0 19.26G/31.33G (61%) ✅\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 12817.4±4106.6 MB/s, size: 235.0 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/cuuva/experiment/datasets/vis5class/labels/train.cache... 6471 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 6471/6471 18.5Mit/s 0.0s\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/0000137_02220_d_0000163.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/0000140_00118_d_0000002.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999945_00000_d_0000114.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999972_00000_d_0000158.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999981_00000_d_0000047.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/cuuva/experiment/datasets/vis5class/images/train/9999987_00000_d_0000049.jpg: 1 duplicate labels removed\n",
+      "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 7032.9±4571.8 MB/s, size: 153.1 KB)\n",
+      "\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /home/cuuva/experiment/datasets/vis5class/labels/val... 548 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 548/548 4.2Kit/s 0.1s0.1s\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /home/cuuva/experiment/datasets/vis5class/labels/val.cache\n",
+      "Plotting labels to /home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/labels.jpg... \n",
+      "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.001, momentum=0.937) with parameter groups 77 weight(decay=0.0), 84 weight(decay=0.00053125), 83 bias(decay=0.0)\n",
+      "Image sizes 640 train, 640 val\n",
+      "Using 8 dataloader workers\n",
+      "Logging results to \u001b[1m/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class\u001b[0m\n",
+      "Starting training for 300 epochs...\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      1/300      18.4G      1.445       1.19     0.9667        618        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 5.6it/s 1.6s0.2s\n",
+      "                   all        548      35895      0.526      0.312      0.326      0.191\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      2/300      20.8G      1.409     0.9562     0.9555        790        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:120.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.4it/s 1.4s0.2s\n",
+      "                   all        548      35895      0.536      0.354      0.386      0.226\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      3/300      18.8G       1.39     0.9126     0.9471        610        640: 100% ━━━━━━━━━━━━ 191/191 2.6it/s 1:120.3sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 5.4it/s 1.7s0.2s\n",
+      "                   all        548      35895      0.467       0.36      0.356      0.205\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      4/300        22G      1.378     0.8927     0.9436       1135        640: 100% ━━━━━━━━━━━━ 191/191 2.6it/s 1:120.3sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 4.7it/s 1.9s0.2s\n",
+      "                   all        548      35895      0.539      0.409      0.425      0.243\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      5/300      25.4G      1.349     0.8549     0.9388        714        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.7it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.58      0.402      0.433      0.258\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      6/300      21.1G      1.319     0.8225     0.9321        640        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.7it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.556      0.419      0.447      0.261\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      7/300      16.7G       1.31     0.8102      0.927        847        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.8it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.578      0.417      0.444       0.26\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      8/300      22.1G      1.298     0.7965      0.925        836        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.572       0.42      0.454      0.267\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K      9/300      23.8G       1.29     0.7875     0.9216        958        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.7it/s 1.4s0.2s\n",
+      "                   all        548      35895      0.623      0.433      0.477      0.284\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     10/300      21.9G      1.275     0.7749       0.92        845        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.8it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.609      0.431      0.474      0.281\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     11/300      23.7G      1.266     0.7587     0.9175        857        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.618      0.442      0.482      0.289\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     12/300        23G      1.259     0.7559     0.9144        503        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.611       0.45      0.489      0.292\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     13/300      19.3G      1.253     0.7427     0.9112       1095        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.8it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.601      0.449      0.486      0.286\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     14/300      20.9G      1.246      0.742      0.911        686        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.608      0.467      0.495      0.297\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     15/300      18.8G      1.241     0.7282     0.9084        598        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.648      0.451      0.504      0.304\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     16/300        20G      1.235     0.7257     0.9081       1140        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.628      0.464      0.512      0.305\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     17/300      21.8G      1.228     0.7206     0.9066        514        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.626      0.476      0.518      0.313\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     18/300      18.8G      1.231     0.7161     0.9061        902        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.621      0.466      0.506      0.306\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     19/300      16.6G      1.213     0.7062      0.904        832        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.612       0.48      0.518      0.316\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     20/300      18.7G      1.214     0.7021      0.903        716        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.622      0.484      0.516      0.312\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     21/300      19.1G      1.218     0.7065     0.9038        393        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.641      0.476      0.519      0.316\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     22/300        19G      1.199     0.6923     0.9001        815        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.622      0.471      0.516      0.315\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     23/300      18.9G        1.2      0.691        0.9        912        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.652      0.475      0.525      0.319\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     24/300      18.9G      1.192     0.6794      0.898       1114        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.643      0.487      0.528      0.323\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     25/300      22.8G      1.196      0.682        0.9        880        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.66      0.495      0.545      0.331\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     26/300        19G      1.187     0.6771     0.8983       1148        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.63      0.481      0.532      0.323\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     27/300      19.7G       1.19     0.6749     0.8966       1210        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.3sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.656      0.488      0.543      0.328\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     28/300      21.1G      1.191     0.6745     0.8952        947        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.623      0.503      0.531      0.324\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     29/300      19.8G      1.186     0.6704     0.8943        905        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.675      0.476       0.54      0.326\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     30/300      21.9G      1.179     0.6618     0.8955        560        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.672      0.489       0.54      0.331\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     31/300      19.1G      1.173     0.6644     0.8921        668        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.673      0.494      0.545      0.335\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     32/300      21.4G      1.178     0.6625      0.893        676        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.66      0.494      0.545      0.334\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     33/300      22.4G      1.168      0.653     0.8915        746        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.672      0.497      0.548      0.333\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     34/300      21.9G      1.162     0.6489     0.8903        892        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.651      0.492       0.54      0.329\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     35/300      22.9G       1.16     0.6461     0.8894        639        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.652      0.495      0.545      0.333\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     36/300      19.7G      1.162     0.6476     0.8903       1132        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.662      0.487      0.535      0.328\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     37/300      19.2G      1.156     0.6424     0.8889        966        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.669      0.504       0.55      0.337\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     38/300        19G      1.162     0.6471     0.8897       1098        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.663      0.509      0.552      0.337\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     39/300      19.6G      1.156     0.6399     0.8871        795        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.687      0.489      0.545      0.333\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     40/300      22.7G      1.149     0.6347     0.8869       1149        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.679      0.496      0.547      0.337\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     41/300      18.5G      1.145     0.6289     0.8848        800        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.677      0.491      0.551       0.34\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     42/300      21.2G      1.147     0.6306     0.8872        945        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.666      0.514      0.557      0.343\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     43/300      23.5G      1.147     0.6291     0.8861        772        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.677      0.514       0.56      0.345\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     44/300      20.1G      1.139     0.6218     0.8839        790        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.67      0.499      0.554      0.339\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     45/300        23G      1.142     0.6234     0.8834       1039        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.661      0.504       0.55      0.335\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     46/300      18.9G      1.142     0.6253      0.885        474        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.671      0.498      0.553      0.341\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     47/300      24.4G       1.13     0.6175     0.8819        761        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.679      0.494      0.551      0.339\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     48/300      19.3G      1.136     0.6174     0.8842       1335        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.678      0.508       0.56      0.344\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     49/300      22.5G      1.126     0.6114     0.8816        928        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.683      0.505      0.559      0.345\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     50/300      18.8G       1.13     0.6113     0.8809        636        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.675      0.509       0.56      0.346\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     51/300      19.1G      1.124     0.6089     0.8796        851        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.664      0.515       0.56      0.345\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     52/300      21.7G      1.124     0.6087     0.8811        822        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.685      0.511      0.568      0.347\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     53/300      21.5G      1.121     0.6047     0.8787        539        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.682      0.509       0.56      0.343\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     54/300      23.2G      1.118     0.6022     0.8775        794        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.682      0.518      0.568      0.348\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     55/300      21.1G      1.111     0.5961     0.8784        848        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.692      0.519      0.571       0.35\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     56/300      18.3G      1.111      0.593     0.8785        762        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.67      0.515      0.561      0.344\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     57/300      21.9G      1.105     0.5927      0.876        661        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.656      0.501      0.556      0.342\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     58/300      19.8G      1.109     0.5936      0.877        668        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.659      0.518      0.561      0.345\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     59/300      17.1G      1.112     0.5944     0.8769        934        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.668       0.53      0.568      0.349\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     60/300      22.3G      1.114     0.5946     0.8777        654        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.666      0.526      0.567       0.35\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     61/300      19.4G      1.106     0.5902      0.876        767        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.673      0.527      0.567      0.352\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     62/300      20.3G      1.109     0.5889     0.8754        842        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.694      0.517       0.57      0.352\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     63/300      21.5G      1.101     0.5854     0.8747        923        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.679      0.515      0.566      0.349\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     64/300      18.4G        1.1     0.5838     0.8746        659        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.698      0.518      0.571      0.352\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     65/300      21.1G      1.097     0.5852     0.8739       1194        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.671      0.527      0.571       0.35\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     66/300        19G      1.094     0.5793     0.8728        602        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.682      0.519      0.567       0.35\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     67/300      18.8G      1.093     0.5783     0.8722        798        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.682      0.522      0.571      0.351\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     68/300      20.9G      1.095     0.5794     0.8736        770        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.663      0.529       0.57      0.351\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     69/300        17G      1.088      0.575     0.8725        737        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.686      0.523      0.572      0.353\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     70/300      19.1G       1.08      0.569     0.8709        806        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.676      0.525      0.574      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     71/300      20.8G       1.09     0.5736     0.8729        866        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.677      0.529      0.573      0.353\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     72/300      20.5G      1.087     0.5741      0.871        639        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.696      0.521      0.575      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     73/300      19.1G      1.076     0.5661     0.8694        886        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895        0.7      0.518      0.575      0.353\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     74/300      18.9G      1.083     0.5652     0.8698        773        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.682      0.524      0.573      0.352\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     75/300      19.4G      1.075     0.5646     0.8692        837        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.686       0.53      0.576      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     76/300      18.3G      1.085     0.5692     0.8706        912        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.704      0.512      0.572      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     77/300      18.7G      1.074     0.5624     0.8697        766        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.685      0.528      0.574      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     78/300      18.7G      1.072     0.5574     0.8686        816        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.703      0.524      0.574      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     79/300        19G      1.064     0.5525     0.8673        503        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.682       0.53      0.575      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     80/300      19.7G      1.073     0.5606      0.866       1023        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.678      0.536      0.576      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     81/300        19G      1.067     0.5565     0.8677        730        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.703       0.52      0.577      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     82/300      21.7G      1.058      0.551     0.8672       1342        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.691      0.523      0.575      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     83/300      21.1G      1.069     0.5587     0.8676        679        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.679      0.532      0.579      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     84/300        21G      1.062     0.5505     0.8675       1074        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.692      0.527      0.577      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     85/300      19.2G      1.062     0.5504     0.8666        579        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.707      0.517      0.573      0.352\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     86/300      20.9G       1.06     0.5507      0.865        746        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.693      0.527      0.574      0.353\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     87/300      19.2G      1.068      0.556     0.8667       1110        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.695      0.528      0.576      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     88/300      19.7G      1.055     0.5491     0.8649        686        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.689      0.532      0.575      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     89/300      19.3G      1.058     0.5491     0.8651        911        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.689      0.522      0.574      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     90/300      24.9G       1.06     0.5457     0.8637        892        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.69      0.527      0.573      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     91/300        19G      1.054     0.5454     0.8625        638        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.699      0.528      0.579      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     92/300      22.3G      1.056     0.5456      0.864        538        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.679      0.541      0.579      0.359\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     93/300      21.8G      1.057     0.5452     0.8633        828        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.688      0.531      0.575      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     94/300      18.3G      1.043     0.5369     0.8614        891        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.694      0.534      0.576      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     95/300      21.7G      1.037     0.5346     0.8609        885        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.696       0.53      0.579      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     96/300        19G      1.047     0.5392     0.8633        961        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.698      0.531      0.581      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     97/300        21G      1.045     0.5377      0.862        611        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.688      0.532      0.579      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     98/300      19.5G      1.042     0.5351     0.8637       1026        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.695      0.531      0.577      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K     99/300      20.9G       1.04     0.5328     0.8602        550        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.692      0.532      0.577      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    100/300      24.8G      1.039     0.5343      0.861        669        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.69      0.526      0.577      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    101/300      21.1G      1.032     0.5306     0.8611        835        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.699      0.529      0.577      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    102/300      18.9G      1.037     0.5321     0.8609        943        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.699      0.525      0.578      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    103/300      16.9G      1.028     0.5275     0.8587       1033        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.699      0.523      0.576      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    104/300      19.4G      1.034     0.5272     0.8605        664        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.696      0.524      0.575      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    105/300      18.8G      1.034     0.5285     0.8597        795        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.686      0.531      0.574      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    106/300      19.5G      1.032     0.5272     0.8589        807        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.697      0.529      0.577      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    107/300      18.1G       1.03     0.5277     0.8602        519        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.688      0.531      0.577      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    108/300      19.2G       1.03     0.5272     0.8587       1017        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.695      0.524      0.575      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    109/300      20.2G      1.028     0.5258     0.8587        755        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.686       0.53      0.572      0.353\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    110/300      23.9G      1.019     0.5197     0.8564        594        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.681       0.53      0.574      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    111/300      21.2G       1.03     0.5242     0.8571        655        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.674      0.538      0.576      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    112/300      21.1G      1.017     0.5173     0.8562        667        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.676      0.537      0.576      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    113/300      22.1G      1.019      0.518     0.8554        702        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.689      0.528      0.577      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    114/300      20.8G      1.019     0.5173     0.8568        547        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.695       0.53      0.578      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    115/300      22.4G      1.015     0.5159     0.8547        700        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.682      0.535      0.577      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    116/300      21.6G      1.007     0.5125     0.8559        803        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895        0.7      0.526      0.578      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    117/300      20.6G      1.009     0.5123     0.8544        878        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.702      0.522      0.577      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    118/300      18.1G      1.018     0.5164     0.8554        649        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.686      0.528      0.578      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    119/300        23G      1.009      0.512     0.8548        646        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.689       0.53       0.58      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    120/300      21.7G      1.007     0.5117     0.8556       1382        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.688      0.533      0.579      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    121/300      22.9G      1.008       0.51     0.8536        877        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.697      0.529      0.578      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    122/300      16.6G      1.009     0.5124     0.8543        720        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:100.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895        0.7      0.528      0.579      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    123/300      23.7G      1.009     0.5111     0.8533        957        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.697      0.528       0.58      0.358\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    124/300      21.9G          1     0.5067     0.8533        641        640: 100% ━━━━━━━━━━━━ 191/191 2.6it/s 1:120.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.702      0.521      0.578      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    125/300        21G      1.004     0.5091     0.8546       1118        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:120.3sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.9it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.694      0.525      0.577      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    126/300      19.8G      1.007     0.5086     0.8551        642        640: 100% ━━━━━━━━━━━━ 191/191 2.6it/s 1:130.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.689       0.53      0.578      0.357\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    127/300      20.9G     0.9983     0.5042     0.8513        732        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895       0.69      0.529      0.578      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    128/300      18.4G     0.9943     0.5024     0.8525        541        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.701      0.523      0.577      0.356\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    129/300      19.5G      1.002     0.5059     0.8532       1128        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.0it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.693      0.528      0.576      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    130/300      21.3G     0.9956     0.5035     0.8513        678        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.2it/s 1.2s0.2s\n",
+      "                   all        548      35895      0.691      0.529      0.578      0.355\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    131/300      22.2G     0.9982     0.5033     0.8507        883        640: 100% ━━━━━━━━━━━━ 191/191 2.6it/s 1:120.3sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 6.7it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.694      0.527      0.577      0.354\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n",
+      "\u001b[K    132/300      18.4G     0.9902     0.4993     0.8521        736        640: 100% ━━━━━━━━━━━━ 191/191 2.7it/s 1:110.2sss\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 7.1it/s 1.3s0.2s\n",
+      "                   all        548      35895      0.696      0.526      0.576      0.354\n",
+      "\u001b[34m\u001b[1mEarlyStopping: \u001b[0mTraining stopped early as no improvement observed in last 40 epochs. Best results observed at epoch 92, best model saved as best.pt.\n",
+      "To update EarlyStopping(patience=40) pass a new patience value, i.e. `patience=300` or use `patience=0` to disable EarlyStopping.\n",
+      "\n",
+      "132 epochs completed in 2.655 hours.\n",
+      "Optimizer stripped from /home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/last.pt, 52.0MB\n",
+      "Optimizer stripped from /home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.pt, 52.0MB\n",
+      "\n",
+      "Validating /home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.pt...\n",
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "Model summary (fused): 92 layers, 25,842,655 parameters, 0 gradients, 78.7 GFLOPs\n",
+      "\u001b[K                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% ━━━━━━━━━━━━ 9/9 2.6it/s 3.4s0.2s\n",
+      "                   all        548      35895      0.677      0.541      0.579      0.359\n",
+      "                person        531      13969      0.658      0.476      0.532      0.233\n",
+      "                   car        517      16039      0.814      0.799      0.845      0.608\n",
+      "                 truck        266        750      0.581      0.384      0.419      0.274\n",
+      "                   bus        131        251      0.762      0.594      0.634      0.469\n",
+      "                 motor        485       4886      0.569      0.451      0.464      0.211\n",
+      "Speed: 0.1ms preprocess, 2.3ms inference, 0.0ms loss, 0.8ms postprocess per image\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load a pretrained YOLO11n model\n",
+    "model = YOLO('yolov8m.pt')\n",
+    "\n",
+    "train_results = model.train(\n",
+    "    data=\"/home/cuuva/experiment/vis5class_exp/vis5class.yaml\", #['person','car', 'truck', 'bus', 'motor']\n",
+    "    epochs=300,\n",
+    "    imgsz=640,\n",
+    "    batch=-1,\n",
+    "    device=\"cuda\",\n",
+    "    optimizer = 'AdamW',\n",
+    "    lr0 = 0.001,\n",
+    "    patience = 40,\n",
+    "    project = 'vis5class_v8m',\n",
+    "    name = '5class',\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "681c71ed",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ultralytics 8.3.225 🚀 Python-3.10.18 torch-2.9.1+cu128 CUDA:0 (NVIDIA GeForce RTX 5090, 32087MiB)\n",
+      "Model summary (fused): 92 layers, 25,842,655 parameters, 0 gradients, 78.7 GFLOPs\n",
+      "\n",
+      "\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from '/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 9, 8400) (49.6 MB)\n",
+      "\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m starting export with onnx 1.19.1 opset 20...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m slimming with onnxslim 0.1.71...\n",
+      "\u001b[34m\u001b[1mONNX:\u001b[0m export success ✅ 0.7s, saved as '/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.onnx' (98.8 MB)\n",
+      "\n",
+      "Export complete (0.8s)\n",
+      "Results saved to \u001b[1m/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights\u001b[0m\n",
+      "Predict:         yolo predict task=detect model=/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.onnx imgsz=640  \n",
+      "Validate:        yolo val task=detect model=/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.onnx imgsz=640 data=/home/cuuva/experiment/vis5class_exp/vis5class.yaml  \n",
+      "Visualize:       https://netron.app\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.onnx'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = YOLO(\"/home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class/weights/best.pt\")\n",
+    "model.export(format=\"onnx\", imgsz=640, device=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "48b48641",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "1stagedetect",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

vis5class_exp/vis5class_v8m/5class/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/vis5class_exp/vis5class.yaml
+epochs: 300
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: vis5class_v8m
+name: 5class
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/vis5class_exp/vis5class_v8m/5class

vis5class_exp/vis5class_v8m/5class/results.csv

@@ -0,0 +1,133 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,72.7568,1.44479,1.19038,0.9667,0.52566,0.31226,0.32582,0.1911,1.43647,1.18109,0.94877,0.0671728,0.000331588,0.000331588
+2,146.528,1.40881,0.95622,0.95553,0.5356,0.35396,0.38618,0.22625,1.39214,0.92107,0.93017,0.0341706,0.000662727,0.000662727
+3,220.972,1.38951,0.91262,0.94708,0.46726,0.35979,0.35628,0.20499,1.42798,0.92396,0.94258,0.00116619,0.000991666,0.000991666
+4,295.999,1.37759,0.89274,0.94359,0.53905,0.40865,0.42472,0.24325,1.38982,0.87942,0.93583,0.0009901,0.0009901,0.0009901
+5,369.108,1.34903,0.85488,0.93877,0.57967,0.40161,0.43275,0.25839,1.35015,0.90369,0.92444,0.0009868,0.0009868,0.0009868
+6,441.547,1.31924,0.82247,0.93214,0.55561,0.41851,0.44732,0.261,1.33912,0.84953,0.92315,0.0009835,0.0009835,0.0009835
+7,513.863,1.3099,0.81025,0.92703,0.57822,0.41739,0.44369,0.26042,1.37561,0.84721,0.93165,0.0009802,0.0009802,0.0009802
+8,586.151,1.29848,0.79646,0.92496,0.57232,0.42032,0.45419,0.2672,1.32583,0.80563,0.9213,0.0009769,0.0009769,0.0009769
+9,658.669,1.28968,0.7875,0.9216,0.62341,0.43253,0.47696,0.28393,1.30096,0.83514,0.90956,0.0009736,0.0009736,0.0009736
+10,731.115,1.27546,0.77488,0.91999,0.6093,0.43106,0.47425,0.28075,1.31621,0.79459,0.9158,0.0009703,0.0009703,0.0009703
+11,803.401,1.26559,0.75875,0.91754,0.61841,0.44194,0.48246,0.28928,1.29203,0.7826,0.90953,0.000967,0.000967,0.000967
+12,875.713,1.25864,0.75592,0.91442,0.61122,0.44982,0.48905,0.29168,1.30185,0.78002,0.90787,0.0009637,0.0009637,0.0009637
+13,948.224,1.2525,0.74269,0.91121,0.60124,0.4494,0.48587,0.28626,1.30836,0.7826,0.90989,0.0009604,0.0009604,0.0009604
+14,1020.71,1.24633,0.74201,0.91098,0.60845,0.46694,0.49534,0.29667,1.29689,0.78034,0.91402,0.0009571,0.0009571,0.0009571
+15,1093.09,1.24055,0.72816,0.90845,0.64826,0.4511,0.50353,0.30391,1.26609,0.76508,0.89919,0.0009538,0.0009538,0.0009538
+16,1165.42,1.23457,0.72571,0.90812,0.62844,0.46435,0.5121,0.30498,1.27594,0.75764,0.90386,0.0009505,0.0009505,0.0009505
+17,1237.76,1.22804,0.72059,0.90655,0.62564,0.47582,0.51764,0.31286,1.26774,0.74107,0.90222,0.0009472,0.0009472,0.0009472
+18,1310.08,1.23115,0.71606,0.90609,0.62078,0.46647,0.50553,0.3059,1.27465,0.75678,0.90188,0.0009439,0.0009439,0.0009439
+19,1382.39,1.21313,0.70619,0.90398,0.61229,0.48042,0.51823,0.31552,1.26788,0.7552,0.90245,0.0009406,0.0009406,0.0009406
+20,1454.67,1.21403,0.70214,0.90304,0.62203,0.48408,0.51592,0.31217,1.25737,0.73259,0.90361,0.0009373,0.0009373,0.0009373
+21,1527.03,1.21845,0.70646,0.90377,0.64118,0.47577,0.51886,0.31596,1.25554,0.748,0.89879,0.000934,0.000934,0.000934
+22,1599.52,1.19854,0.69233,0.90007,0.62212,0.47112,0.51607,0.31454,1.25119,0.73104,0.90035,0.0009307,0.0009307,0.0009307
+23,1671.84,1.19967,0.69096,0.90002,0.65247,0.47538,0.52464,0.31917,1.24608,0.72681,0.89989,0.0009274,0.0009274,0.0009274
+24,1744.1,1.19214,0.67943,0.89803,0.64346,0.48673,0.5285,0.32305,1.24095,0.72563,0.89791,0.0009241,0.0009241,0.0009241
+25,1816.5,1.19568,0.68199,0.89997,0.65985,0.495,0.5448,0.33145,1.24235,0.72473,0.89875,0.0009208,0.0009208,0.0009208
+26,1888.78,1.18738,0.67711,0.89834,0.6301,0.48075,0.53157,0.32252,1.23859,0.73707,0.89891,0.0009175,0.0009175,0.0009175
+27,1961.09,1.19036,0.67488,0.89663,0.65624,0.48764,0.54258,0.32831,1.23368,0.71317,0.89764,0.0009142,0.0009142,0.0009142
+28,2033.4,1.19103,0.67453,0.89523,0.62319,0.50315,0.53056,0.32432,1.23825,0.72077,0.89874,0.0009109,0.0009109,0.0009109
+29,2105.65,1.18587,0.67044,0.89428,0.67528,0.47607,0.53993,0.326,1.22415,0.71254,0.89454,0.0009076,0.0009076,0.0009076
+30,2177.87,1.17865,0.66183,0.89554,0.67226,0.48936,0.54047,0.33084,1.22137,0.71192,0.89395,0.0009043,0.0009043,0.0009043
+31,2250.1,1.17282,0.66441,0.89208,0.67328,0.4936,0.54521,0.33471,1.21474,0.70494,0.89327,0.000901,0.000901,0.000901
+32,2322.44,1.1782,0.66251,0.89295,0.66042,0.49383,0.54527,0.33374,1.22493,0.70325,0.89339,0.0008977,0.0008977,0.0008977
+33,2394.66,1.16764,0.65303,0.89151,0.67183,0.497,0.5482,0.33305,1.23193,0.69596,0.89748,0.0008944,0.0008944,0.0008944
+34,2466.88,1.16184,0.64893,0.89027,0.65086,0.49235,0.53969,0.32907,1.21816,0.70487,0.89324,0.0008911,0.0008911,0.0008911
+35,2539.16,1.15984,0.64608,0.88939,0.65227,0.49514,0.54504,0.33303,1.22438,0.69745,0.89576,0.0008878,0.0008878,0.0008878
+36,2611.39,1.16221,0.64757,0.89028,0.66156,0.4865,0.53504,0.32798,1.22514,0.70801,0.89295,0.0008845,0.0008845,0.0008845
+37,2683.66,1.1559,0.64241,0.88895,0.66886,0.50362,0.55028,0.33661,1.20028,0.69788,0.88951,0.0008812,0.0008812,0.0008812
+38,2756.07,1.16184,0.64711,0.8897,0.66301,0.50888,0.55185,0.33725,1.21322,0.69086,0.89153,0.0008779,0.0008779,0.0008779
+39,2828.43,1.15611,0.63988,0.88705,0.68708,0.48925,0.54485,0.33338,1.21991,0.70563,0.89266,0.0008746,0.0008746,0.0008746
+40,2900.69,1.14893,0.63472,0.88685,0.679,0.49606,0.54707,0.33667,1.21558,0.69434,0.89155,0.0008713,0.0008713,0.0008713
+41,2973.01,1.14496,0.62893,0.88481,0.67696,0.49122,0.55066,0.33988,1.21175,0.6891,0.8921,0.000868,0.000868,0.000868
+42,3045.39,1.14668,0.63065,0.88718,0.66638,0.51362,0.55658,0.3427,1.21471,0.69933,0.89103,0.0008647,0.0008647,0.0008647
+43,3117.82,1.14663,0.62913,0.88614,0.67651,0.51428,0.55969,0.34461,1.20413,0.69234,0.8909,0.0008614,0.0008614,0.0008614
+44,3190.16,1.1391,0.62178,0.88394,0.66959,0.4986,0.55404,0.33902,1.21575,0.68684,0.89197,0.0008581,0.0008581,0.0008581
+45,3262.53,1.14195,0.6234,0.88342,0.66141,0.50379,0.54965,0.33541,1.20795,0.69653,0.89144,0.0008548,0.0008548,0.0008548
+46,3334.78,1.14212,0.62532,0.88499,0.6708,0.49769,0.55324,0.34147,1.20663,0.69257,0.88954,0.0008515,0.0008515,0.0008515
+47,3407.25,1.13047,0.61754,0.88195,0.6788,0.49389,0.55125,0.33948,1.20174,0.68798,0.89172,0.0008482,0.0008482,0.0008482
+48,3479.52,1.13584,0.6174,0.88417,0.67839,0.50833,0.56009,0.34431,1.207,0.68707,0.89112,0.0008449,0.0008449,0.0008449
+49,3551.83,1.12563,0.61143,0.88157,0.6831,0.50507,0.55869,0.34467,1.21072,0.68338,0.89356,0.0008416,0.0008416,0.0008416
+50,3624.15,1.1301,0.6113,0.88095,0.67488,0.50928,0.55984,0.34559,1.20584,0.68578,0.8908,0.0008383,0.0008383,0.0008383
+51,3696.59,1.12386,0.60888,0.8796,0.66433,0.51488,0.56042,0.34534,1.2089,0.68237,0.89281,0.000835,0.000835,0.000835
+52,3768.83,1.12375,0.6087,0.88108,0.68546,0.51061,0.56772,0.34676,1.20313,0.68138,0.88888,0.0008317,0.0008317,0.0008317
+53,3841.24,1.12149,0.60466,0.8787,0.682,0.50907,0.56022,0.3427,1.20168,0.68234,0.89215,0.0008284,0.0008284,0.0008284
+54,3913.56,1.11817,0.60223,0.87751,0.6822,0.51812,0.56755,0.34812,1.20187,0.67429,0.88937,0.0008251,0.0008251,0.0008251
+55,3985.94,1.11051,0.59606,0.8784,0.69197,0.51877,0.57068,0.34954,1.19689,0.67102,0.88849,0.0008218,0.0008218,0.0008218
+56,4058.24,1.11085,0.59297,0.87846,0.66953,0.51478,0.56063,0.34444,1.1969,0.6731,0.89011,0.0008185,0.0008185,0.0008185
+57,4130.61,1.1046,0.5927,0.87597,0.65563,0.50094,0.55575,0.34249,1.19594,0.68285,0.88795,0.0008152,0.0008152,0.0008152
+58,4202.88,1.10851,0.59355,0.87697,0.65894,0.51787,0.56094,0.34476,1.19487,0.68033,0.89029,0.0008119,0.0008119,0.0008119
+59,4275.1,1.11166,0.59444,0.87689,0.66819,0.52964,0.56819,0.34948,1.18841,0.67189,0.88718,0.0008086,0.0008086,0.0008086
+60,4347.3,1.11402,0.59459,0.87766,0.66618,0.52623,0.56653,0.35045,1.19258,0.67685,0.88582,0.0008053,0.0008053,0.0008053
+61,4419.61,1.10603,0.59023,0.87597,0.67289,0.5269,0.56668,0.35173,1.19458,0.67252,0.88722,0.000802,0.000802,0.000802
+62,4492.02,1.1089,0.58893,0.87539,0.69442,0.51666,0.57002,0.35218,1.19512,0.67205,0.88742,0.0007987,0.0007987,0.0007987
+63,4564.35,1.10126,0.58544,0.8747,0.67927,0.51548,0.5658,0.34873,1.19728,0.67687,0.88857,0.0007954,0.0007954,0.0007954
+64,4636.68,1.10015,0.58379,0.87463,0.69835,0.51765,0.57147,0.35158,1.1948,0.6743,0.89006,0.0007921,0.0007921,0.0007921
+65,4708.95,1.09685,0.58521,0.87389,0.67123,0.52733,0.571,0.34998,1.20161,0.66962,0.89241,0.0007888,0.0007888,0.0007888
+66,4781.15,1.09412,0.57933,0.87283,0.68204,0.51892,0.56677,0.35045,1.1912,0.66631,0.89006,0.0007855,0.0007855,0.0007855
+67,4853.4,1.09323,0.57828,0.87218,0.68187,0.52194,0.57107,0.35096,1.19295,0.66392,0.89132,0.0007822,0.0007822,0.0007822
+68,4925.57,1.09542,0.57942,0.87359,0.66349,0.52872,0.56969,0.35069,1.1977,0.67358,0.89008,0.0007789,0.0007789,0.0007789
+69,4997.8,1.08848,0.57502,0.87253,0.68603,0.52252,0.5721,0.3527,1.19264,0.66167,0.89018,0.0007756,0.0007756,0.0007756
+70,5070.07,1.0797,0.56895,0.87086,0.67564,0.52518,0.57448,0.3537,1.19413,0.67271,0.88964,0.0007723,0.0007723,0.0007723
+71,5142.4,1.08952,0.57364,0.8729,0.67722,0.52944,0.5732,0.35254,1.1932,0.66443,0.8912,0.000769,0.000769,0.000769
+72,5214.69,1.08708,0.5741,0.87103,0.69565,0.52059,0.57491,0.35386,1.19117,0.66422,0.89011,0.0007657,0.0007657,0.0007657
+73,5287.15,1.07594,0.56612,0.86938,0.69976,0.51829,0.5745,0.35339,1.18939,0.66648,0.88708,0.0007624,0.0007624,0.0007624
+74,5359.37,1.08267,0.5652,0.86979,0.68236,0.52436,0.5731,0.35212,1.19171,0.6614,0.88856,0.0007591,0.0007591,0.0007591
+75,5431.66,1.07528,0.56457,0.86918,0.68625,0.52982,0.57569,0.35554,1.1933,0.65658,0.88714,0.0007558,0.0007558,0.0007558
+76,5503.89,1.08461,0.56925,0.87057,0.70377,0.51155,0.572,0.35407,1.19292,0.66601,0.88734,0.0007525,0.0007525,0.0007525
+77,5576.13,1.07366,0.56236,0.86966,0.68546,0.52834,0.57438,0.3551,1.1946,0.66593,0.88785,0.0007492,0.0007492,0.0007492
+78,5648.34,1.07155,0.55735,0.86862,0.70273,0.5239,0.57413,0.35533,1.18901,0.66374,0.88651,0.0007459,0.0007459,0.0007459
+79,5720.68,1.06394,0.55246,0.8673,0.68239,0.52979,0.57519,0.35688,1.19014,0.6592,0.88768,0.0007426,0.0007426,0.0007426
+80,5792.96,1.07301,0.56063,0.86597,0.67787,0.53589,0.57642,0.35638,1.18833,0.66365,0.88654,0.0007393,0.0007393,0.0007393
+81,5865.13,1.06688,0.55651,0.8677,0.70261,0.52034,0.5774,0.35753,1.18545,0.66171,0.88895,0.000736,0.000736,0.000736
+82,5937.49,1.05782,0.55102,0.86717,0.69084,0.52252,0.57526,0.35372,1.18495,0.66243,0.88584,0.0007327,0.0007327,0.0007327
+83,6009.86,1.06942,0.55865,0.86761,0.67928,0.53153,0.57923,0.35659,1.18692,0.65926,0.88678,0.0007294,0.0007294,0.0007294
+84,6082.16,1.06156,0.55052,0.86748,0.69249,0.52683,0.57718,0.3554,1.18747,0.66281,0.88825,0.0007261,0.0007261,0.0007261
+85,6154.46,1.06163,0.5504,0.86661,0.70651,0.51678,0.57279,0.35238,1.18784,0.66091,0.88734,0.0007228,0.0007228,0.0007228
+86,6226.73,1.05978,0.55075,0.86498,0.69302,0.52674,0.57401,0.3535,1.18608,0.66251,0.88808,0.0007195,0.0007195,0.0007195
+87,6298.97,1.06763,0.55596,0.86671,0.69507,0.52814,0.57564,0.35602,1.18863,0.6619,0.88688,0.0007162,0.0007162,0.0007162
+88,6371.21,1.05527,0.54906,0.86485,0.68936,0.53185,0.57534,0.3559,1.18632,0.66433,0.88541,0.0007129,0.0007129,0.0007129
+89,6443.46,1.05816,0.54908,0.86506,0.68943,0.52236,0.57442,0.35652,1.18542,0.66013,0.88579,0.0007096,0.0007096,0.0007096
+90,6515.77,1.0599,0.54574,0.86374,0.68979,0.52658,0.5734,0.35609,1.1843,0.65965,0.88657,0.0007063,0.0007063,0.0007063
+91,6588.09,1.05442,0.54542,0.86247,0.69883,0.52824,0.57886,0.35701,1.18908,0.66049,0.8874,0.000703,0.000703,0.000703
+92,6660.36,1.05574,0.54564,0.86405,0.67881,0.54114,0.57866,0.35908,1.1866,0.65861,0.88596,0.0006997,0.0006997,0.0006997
+93,6732.82,1.05693,0.54519,0.86332,0.68776,0.53119,0.57482,0.35621,1.18658,0.6616,0.88643,0.0006964,0.0006964,0.0006964
+94,6805.04,1.04346,0.53688,0.86144,0.69365,0.53376,0.5761,0.35619,1.18791,0.66342,0.88622,0.0006931,0.0006931,0.0006931
+95,6877.29,1.03656,0.53459,0.86088,0.69556,0.53029,0.57856,0.35784,1.19223,0.66052,0.88895,0.0006898,0.0006898,0.0006898
+96,6949.37,1.04681,0.53917,0.86335,0.69806,0.53114,0.58105,0.35808,1.19037,0.65811,0.88828,0.0006865,0.0006865,0.0006865
+97,7021.67,1.04488,0.53766,0.86197,0.68827,0.5324,0.57903,0.35806,1.18978,0.65673,0.88708,0.0006832,0.0006832,0.0006832
+98,7093.91,1.04218,0.53513,0.8637,0.69459,0.53054,0.57667,0.35815,1.18858,0.65629,0.88636,0.0006799,0.0006799,0.0006799
+99,7166.2,1.03995,0.53279,0.86021,0.69154,0.53212,0.57719,0.35785,1.1884,0.65631,0.88687,0.0006766,0.0006766,0.0006766
+100,7238.52,1.03859,0.53426,0.86097,0.68992,0.52582,0.5771,0.35559,1.19059,0.65758,0.88754,0.0006733,0.0006733,0.0006733
+101,7310.87,1.03222,0.5306,0.86112,0.69893,0.52928,0.57677,0.3558,1.19042,0.65712,0.88819,0.00067,0.00067,0.00067
+102,7383.01,1.037,0.53206,0.86088,0.69906,0.52487,0.57772,0.35539,1.18846,0.65588,0.8884,0.0006667,0.0006667,0.0006667
+103,7455.24,1.0281,0.52749,0.85875,0.6991,0.52327,0.57584,0.35528,1.18785,0.65254,0.8885,0.0006634,0.0006634,0.0006634
+104,7527.47,1.03388,0.52716,0.86047,0.69553,0.52439,0.57501,0.35434,1.18834,0.65659,0.88853,0.0006601,0.0006601,0.0006601
+105,7599.69,1.03391,0.52851,0.85969,0.68635,0.53102,0.57379,0.35429,1.18981,0.66117,0.88868,0.0006568,0.0006568,0.0006568
+106,7671.97,1.03233,0.52718,0.85894,0.697,0.52916,0.57698,0.355,1.1898,0.66,0.88799,0.0006535,0.0006535,0.0006535
+107,7744.21,1.02989,0.52766,0.86019,0.68845,0.5312,0.57663,0.35424,1.19084,0.65885,0.88822,0.0006502,0.0006502,0.0006502
+108,7816.41,1.03038,0.52719,0.8587,0.69494,0.52434,0.57476,0.3537,1.19158,0.65954,0.88774,0.0006469,0.0006469,0.0006469
+109,7888.67,1.02772,0.5258,0.85871,0.6863,0.52964,0.57246,0.35286,1.19185,0.66012,0.88833,0.0006436,0.0006436,0.0006436
+110,7960.92,1.01932,0.51972,0.85635,0.68106,0.53027,0.57405,0.35411,1.18992,0.66047,0.88792,0.0006403,0.0006403,0.0006403
+111,8033.14,1.03017,0.5242,0.85706,0.6738,0.53844,0.57559,0.35547,1.18852,0.66085,0.8874,0.000637,0.000637,0.000637
+112,8105.43,1.01654,0.51729,0.85625,0.67623,0.53686,0.57646,0.3551,1.18867,0.65712,0.88721,0.0006337,0.0006337,0.0006337
+113,8177.78,1.01925,0.51799,0.8554,0.68948,0.52755,0.57733,0.35621,1.1897,0.65658,0.8878,0.0006304,0.0006304,0.0006304
+114,8250.07,1.01855,0.51732,0.85675,0.69542,0.52984,0.57751,0.35644,1.19212,0.65599,0.88826,0.0006271,0.0006271,0.0006271
+115,8322.49,1.01451,0.51586,0.85473,0.68239,0.53452,0.57679,0.35638,1.19069,0.65772,0.88853,0.0006238,0.0006238,0.0006238
+116,8394.67,1.00699,0.51249,0.8559,0.69969,0.5265,0.57752,0.35535,1.19107,0.6581,0.88906,0.0006205,0.0006205,0.0006205
+117,8466.95,1.0094,0.51229,0.85435,0.70182,0.52175,0.57716,0.35571,1.1901,0.65652,0.8898,0.0006172,0.0006172,0.0006172
+118,8539.22,1.01758,0.51645,0.85537,0.68603,0.52839,0.57753,0.35669,1.19028,0.65602,0.8903,0.0006139,0.0006139,0.0006139
+119,8611.47,1.00895,0.51196,0.85482,0.68942,0.53026,0.57957,0.35736,1.19022,0.65459,0.89051,0.0006106,0.0006106,0.0006106
+120,8683.69,1.00709,0.51166,0.85558,0.68847,0.53302,0.57853,0.35673,1.19074,0.65581,0.8904,0.0006073,0.0006073,0.0006073
+121,8756.02,1.00848,0.50997,0.85363,0.69659,0.52931,0.57847,0.35762,1.19145,0.65595,0.89088,0.000604,0.000604,0.000604
+122,8828.23,1.00919,0.51241,0.85425,0.70043,0.52817,0.57946,0.35727,1.19161,0.65648,0.89055,0.0006007,0.0006007,0.0006007
+123,8900.5,1.00918,0.51109,0.85328,0.69719,0.52818,0.58011,0.35753,1.19103,0.65598,0.89025,0.0005974,0.0005974,0.0005974
+124,8974.49,1.00047,0.5067,0.85325,0.7024,0.5209,0.57788,0.35653,1.19385,0.65601,0.891,0.0005941,0.0005941,0.0005941
+125,9048.16,1.00401,0.50905,0.85464,0.69441,0.52487,0.57741,0.35698,1.19312,0.65498,0.89075,0.0005908,0.0005908,0.0005908
+126,9122.38,1.00738,0.50857,0.85508,0.68938,0.53035,0.57848,0.35667,1.19199,0.65598,0.89048,0.0005875,0.0005875,0.0005875
+127,9194.96,0.99834,0.50425,0.85134,0.68983,0.52851,0.57842,0.3559,1.19197,0.6546,0.89047,0.0005842,0.0005842,0.0005842
+128,9267.25,0.99429,0.50238,0.85247,0.70076,0.52259,0.57722,0.35562,1.19217,0.65469,0.89068,0.0005809,0.0005809,0.0005809
+129,9339.76,1.00197,0.50593,0.85321,0.69296,0.52789,0.57646,0.35483,1.19223,0.65465,0.89073,0.0005776,0.0005776,0.0005776
+130,9412.1,0.99559,0.50348,0.85127,0.6909,0.52884,0.57788,0.35486,1.19113,0.65186,0.89076,0.0005743,0.0005743,0.0005743
+131,9486.26,0.99815,0.50326,0.85075,0.69389,0.52696,0.57719,0.35445,1.19055,0.65211,0.89079,0.000571,0.000571,0.000571
+132,9558.8,0.9902,0.49932,0.85206,0.69645,0.5264,0.57649,0.35434,1.19113,0.65155,0.8908,0.0005677,0.0005677,0.0005677

vis6class_exp/test.ipynb

@@ -0,0 +1,348 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "817586c7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "🔍 Checking split: train  (files: 6471)\n",
+      "\n",
+      "🔍 Checking split: val  (files: 548)\n",
+      "\n",
+      "🔍 Checking split: test  (files: 1610)\n",
+      "\n",
+      "📌 클래스 통계 결과:\n",
+      " - Class 0: 147747 개\n",
+      " - Class 1: 187005 개\n",
+      " - Class 2: 32702 개\n",
+      " - Class 3: 16284 개\n",
+      " - Class 4: 9117 개\n",
+      " - Class 5: 40378 개\n",
+      "\n",
+      "총 클래스 종류: 6\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from collections import Counter\n",
+    "\n",
+    "# label_root = \"/home/cuuva/experiment/datasets/VisDrone/labels copy\"\n",
+    "label_root = \"/home/cuuva/experiment/datasets/VisDrone/labels\"\n",
+    "splits = [\"train\", \"val\",'test']\n",
+    "\n",
+    "class_counter = Counter()\n",
+    "\n",
+    "for split in splits:\n",
+    "    split_path = os.path.join(label_root, split)\n",
+    "    \n",
+    "    # 라벨 txt 파일 탐색\n",
+    "    label_files = [f for f in os.listdir(split_path) if f.endswith(\".txt\")]\n",
+    "    \n",
+    "    print(f\"\\n🔍 Checking split: {split}  (files: {len(label_files)})\")\n",
+    "\n",
+    "    for file in label_files:\n",
+    "        file_path = os.path.join(split_path, file)\n",
+    "        with open(file_path, \"r\") as f:\n",
+    "            for line in f.readlines():\n",
+    "                if line.strip():  # 빈 줄 제거\n",
+    "                    class_id = line.split()[0]  # 첫번째 값 = 클래스\n",
+    "                    class_counter[class_id] += 1\n",
+    "\n",
+    "# 최종 결과 출력\n",
+    "print(\"\\n📌 클래스 통계 결과:\")\n",
+    "for cls, count in sorted(class_counter.items(), key=lambda x: int(x[0])):\n",
+    "    print(f\" - Class {cls}: {count} 개\")\n",
+    "\n",
+    "print(f\"\\n총 클래스 종류: {len(class_counter)}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "35cf2381",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "📂 Updating: train (files: 6471)\n",
+      "\n",
+      "📂 Updating: val (files: 548)\n",
+      "\n",
+      "📂 Updating: test (files: 1610)\n",
+      "\n",
+      "✅ 라벨 클래스 번호 재정렬 완료!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "label_root = \"/home/cuuva/experiment/datasets/VisDrone/labels\"\n",
+    "splits = [\"train\", \"val\", \"test\"]\n",
+    "\n",
+    "# 클래스 재매핑 설정\n",
+    "mapping = {\n",
+    "    \"0\": \"0\",   # person stays 0\n",
+    "    \"1\": \"1\",   # car stays 1\n",
+    "    \"2\": \"5\",   # van -> 5\n",
+    "    \"3\": \"2\",   # truck -> 2\n",
+    "    \"4\": \"3\",   # bus -> 3\n",
+    "    \"5\": \"4\"    # motor -> 4\n",
+    "}\n",
+    "\n",
+    "for split in splits:\n",
+    "    split_path = os.path.join(label_root, split)\n",
+    "    label_files = [f for f in os.listdir(split_path) if f.endswith(\".txt\")]\n",
+    "\n",
+    "    print(f\"\\n📂 Updating: {split} (files: {len(label_files)})\")\n",
+    "\n",
+    "    for file in label_files:\n",
+    "        file_path = os.path.join(split_path, file)\n",
+    "\n",
+    "        new_lines = []\n",
+    "        with open(file_path, \"r\") as f:\n",
+    "            for line in f.readlines():\n",
+    "                if line.strip():\n",
+    "                    parts = line.split()\n",
+    "                    cls = parts[0]\n",
+    "                    parts[0] = mapping[cls]  # 클래스 번호 변경\n",
+    "                    new_lines.append(\" \".join(parts) + \"\\n\")\n",
+    "\n",
+    "        # 덮어쓰기\n",
+    "        with open(file_path, \"w\") as f:\n",
+    "            f.writelines(new_lines)\n",
+    "\n",
+    "print(\"\\n✅ 라벨 클래스 번호 재정렬 완료!\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3fdd6e44",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "🔍 Checking split: train  (files: 6471)\n",
+      "\n",
+      "🔍 Checking split: val  (files: 548)\n",
+      "\n",
+      "🔍 Checking split: test  (files: 1610)\n",
+      "\n",
+      "📌 클래스 통계 결과:\n",
+      " - Class 0: 147747 개\n",
+      " - Class 1: 187005 개\n",
+      " - Class 2: 16284 개\n",
+      " - Class 3: 9117 개\n",
+      " - Class 4: 40378 개\n",
+      " - Class 5: 32702 개\n",
+      "\n",
+      "총 클래스 종류: 6\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from collections import Counter\n",
+    "\n",
+    "# label_root = \"/home/cuuva/experiment/datasets/VisDrone/labels copy\"\n",
+    "label_root = \"/home/cuuva/experiment/datasets/VisDrone/labels\"\n",
+    "splits = [\"train\", \"val\",'test']\n",
+    "\n",
+    "class_counter = Counter()\n",
+    "\n",
+    "for split in splits:\n",
+    "    split_path = os.path.join(label_root, split)\n",
+    "    \n",
+    "    # 라벨 txt 파일 탐색\n",
+    "    label_files = [f for f in os.listdir(split_path) if f.endswith(\".txt\")]\n",
+    "    \n",
+    "    print(f\"\\n🔍 Checking split: {split}  (files: {len(label_files)})\")\n",
+    "\n",
+    "    for file in label_files:\n",
+    "        file_path = os.path.join(split_path, file)\n",
+    "        with open(file_path, \"r\") as f:\n",
+    "            for line in f.readlines():\n",
+    "                if line.strip():  # 빈 줄 제거\n",
+    "                    class_id = line.split()[0]  # 첫번째 값 = 클래스\n",
+    "                    class_counter[class_id] += 1\n",
+    "\n",
+    "# 최종 결과 출력\n",
+    "print(\"\\n📌 클래스 통계 결과:\")\n",
+    "for cls, count in sorted(class_counter.items(), key=lambda x: int(x[0])):\n",
+    "    print(f\" - Class {cls}: {count} 개\")\n",
+    "\n",
+    "print(f\"\\n총 클래스 종류: {len(class_counter)}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ca796e3d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Processing train: 6471 files\n",
+      "Processing val: 548 files\n",
+      "Processing test: 1610 files\n",
+      "Done. All label files updated!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from glob import glob\n",
+    "\n",
+    "# 라벨 매핑\n",
+    "mapping = {\n",
+    "    0: 0,\n",
+    "    1: 2,\n",
+    "    2: 5,\n",
+    "    3: 4,\n",
+    "    4: 3,\n",
+    "    5: 1\n",
+    "}\n",
+    "\n",
+    "# labels 폴더 경로\n",
+    "base_dir = \"/home/cuuva/experiment/datasets/VisDrone/labels\"\n",
+    "\n",
+    "# train, val, test 모두 처리\n",
+    "splits = [\"train\", \"val\", \"test\"]\n",
+    "\n",
+    "for split in splits:\n",
+    "    label_dir = os.path.join(base_dir, split)\n",
+    "    txt_files = glob(os.path.join(label_dir, \"*.txt\"))\n",
+    "\n",
+    "    print(f\"Processing {split}: {len(txt_files)} files\")\n",
+    "\n",
+    "    for txt_path in txt_files:\n",
+    "        lines = []\n",
+    "        with open(txt_path, \"r\") as f:\n",
+    "            for line in f.readlines():\n",
+    "                parts = line.strip().split()\n",
+    "                if len(parts) < 5:\n",
+    "                    continue\n",
+    "\n",
+    "                old_cls = int(parts[0])\n",
+    "                new_cls = mapping[old_cls]\n",
+    "\n",
+    "                # 클래스만 변경해서 다시 저장\n",
+    "                parts[0] = str(new_cls)\n",
+    "                lines.append(\" \".join(parts))\n",
+    "\n",
+    "        with open(txt_path, \"w\") as f:\n",
+    "            f.write(\"\\n\".join(lines))\n",
+    "\n",
+    "print(\"Done. All label files updated!\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a461857c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "🔍 Checking split: train  (files: 6471)\n",
+      "\n",
+      "🔍 Checking split: val  (files: 548)\n",
+      "\n",
+      "🔍 Checking split: test  (files: 1610)\n",
+      "\n",
+      "📌 클래스 통계 결과:\n",
+      " - Class 0: 147747 개\n",
+      " - Class 1: 32702 개\n",
+      " - Class 2: 187005 개\n",
+      " - Class 3: 40378 개\n",
+      " - Class 4: 9117 개\n",
+      " - Class 5: 16284 개\n",
+      "\n",
+      "총 클래스 종류: 6\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from collections import Counter\n",
+    "\n",
+    "# label_root = \"/home/cuuva/experiment/datasets/VisDrone/labels copy\"\n",
+    "label_root = \"/home/cuuva/experiment/datasets/VisDrone/labels\"\n",
+    "splits = [\"train\", \"val\",'test']\n",
+    "\n",
+    "class_counter = Counter()\n",
+    "\n",
+    "for split in splits:\n",
+    "    split_path = os.path.join(label_root, split)\n",
+    "    \n",
+    "    # 라벨 txt 파일 탐색\n",
+    "    label_files = [f for f in os.listdir(split_path) if f.endswith(\".txt\")]\n",
+    "    \n",
+    "    print(f\"\\n🔍 Checking split: {split}  (files: {len(label_files)})\")\n",
+    "\n",
+    "    for file in label_files:\n",
+    "        file_path = os.path.join(split_path, file)\n",
+    "        with open(file_path, \"r\") as f:\n",
+    "            for line in f.readlines():\n",
+    "                if line.strip():  # 빈 줄 제거\n",
+    "                    class_id = line.split()[0]  # 첫번째 값 = 클래스\n",
+    "                    class_counter[class_id] += 1\n",
+    "\n",
+    "# 최종 결과 출력\n",
+    "print(\"\\n📌 클래스 통계 결과:\")\n",
+    "for cls, count in sorted(class_counter.items(), key=lambda x: int(x[0])):\n",
+    "    print(f\" - Class {cls}: {count} 개\")\n",
+    "\n",
+    "print(f\"\\n총 클래스 종류: {len(class_counter)}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8320460f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "1stagedetect",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

vis6class_exp/vis6class.yaml

@@ -0,0 +1,9 @@
+# path: /home/cuuva/experiment/datasets/VisDrone  # 데이터 경로
+train: /home/cuuva/experiment/datasets/VisDrone/images/train
+val: /home/cuuva/experiment/datasets/VisDrone/images/val
+test: /home/cuuva/experiment/datasets/VisDrone/images/test
+
+# nc: 7
+nc: 6
+
+names: ['person','van', 'car', 'motor', 'bus', 'truck']

vis6class_exp/vis6class_v8m/6class/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/vis6class_exp/vis6class.yaml
+epochs: 300
+time: null
+patience: 40
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: vis6class_v8m
+name: 6class
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/vis6class_exp/vis6class_v8m/6class

vis6class_exp/vis6class_v8m/6class/results.csv

@@ -0,0 +1,101 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,74.1002,1.45177,1.3499,0.97119,0.48954,0.30681,0.30529,0.17932,1.46069,1.21004,0.94941,0.0671728,0.000331588,0.000331588
+2,148.131,1.42041,1.10112,0.96067,0.47059,0.352,0.36077,0.21327,1.41416,1.03289,0.93623,0.0341706,0.000662727,0.000662727
+3,221.858,1.39319,1.03644,0.94917,0.50337,0.35262,0.36769,0.21697,1.42161,1.00914,0.94548,0.00116619,0.000991666,0.000991666
+4,295.795,1.38518,1.018,0.94572,0.52072,0.3747,0.39712,0.23517,1.38396,1.00425,0.93809,0.0009901,0.0009901,0.0009901
+5,369.646,1.35604,0.97151,0.94079,0.55572,0.40298,0.42724,0.25804,1.36183,0.95484,0.92768,0.0009868,0.0009868,0.0009868
+6,443.461,1.32355,0.9374,0.93301,0.56177,0.42047,0.44722,0.27129,1.33378,0.92188,0.92135,0.0009835,0.0009835,0.0009835
+7,517.36,1.31262,0.92344,0.92816,0.5582,0.43973,0.4582,0.27517,1.33844,0.92068,0.92221,0.0009802,0.0009802,0.0009802
+8,591.194,1.30079,0.90833,0.92641,0.57202,0.41992,0.44361,0.27151,1.31729,0.91243,0.91604,0.0009769,0.0009769,0.0009769
+9,665.026,1.29606,0.90336,0.92359,0.57351,0.44143,0.46864,0.2833,1.32878,0.92955,0.91668,0.0009736,0.0009736,0.0009736
+10,738.869,1.27877,0.8829,0.92106,0.57844,0.42265,0.45566,0.27703,1.32715,0.89014,0.91463,0.0009703,0.0009703,0.0009703
+11,812.532,1.26649,0.86183,0.91754,0.58756,0.44204,0.47371,0.28897,1.29562,0.87513,0.91023,0.000967,0.000967,0.000967
+12,886.355,1.26449,0.86083,0.91607,0.60498,0.44684,0.48269,0.29466,1.28648,0.87708,0.90954,0.0009637,0.0009637,0.0009637
+13,960.256,1.25465,0.84375,0.91256,0.59391,0.44503,0.48025,0.2962,1.29084,0.87299,0.90876,0.0009604,0.0009604,0.0009604
+14,1034.01,1.24925,0.84191,0.91249,0.62119,0.45639,0.49158,0.30217,1.3036,0.86918,0.9129,0.0009571,0.0009571,0.0009571
+15,1107.85,1.24384,0.82944,0.90949,0.59543,0.45757,0.49172,0.30291,1.26882,0.84082,0.90175,0.0009538,0.0009538,0.0009538
+16,1181.71,1.23645,0.82577,0.90873,0.60781,0.4736,0.50234,0.30809,1.26924,0.83872,0.90204,0.0009505,0.0009505,0.0009505
+17,1255.6,1.23074,0.81984,0.90732,0.62542,0.45287,0.50038,0.30833,1.27476,0.83562,0.9022,0.0009472,0.0009472,0.0009472
+18,1329.38,1.23136,0.80891,0.90616,0.61224,0.46293,0.50371,0.31596,1.25041,0.82561,0.90028,0.0009439,0.0009439,0.0009439
+19,1403.25,1.21353,0.79899,0.90462,0.6217,0.47534,0.51434,0.31848,1.257,0.82485,0.90221,0.0009406,0.0009406,0.0009406
+20,1477.11,1.21914,0.79852,0.90496,0.63769,0.45614,0.50191,0.31432,1.25189,0.83266,0.90275,0.0009373,0.0009373,0.0009373
+21,1550.91,1.22066,0.79996,0.90467,0.63057,0.47378,0.51174,0.31611,1.25517,0.83242,0.90244,0.000934,0.000934,0.000934
+22,1624.82,1.2011,0.78328,0.90034,0.64121,0.46332,0.51413,0.31872,1.24861,0.81903,0.89995,0.0009307,0.0009307,0.0009307
+23,1699,1.20225,0.779,0.90028,0.62985,0.47157,0.51082,0.31913,1.24698,0.82095,0.90152,0.0009274,0.0009274,0.0009274
+24,1772.77,1.19432,0.76937,0.89887,0.62763,0.47129,0.51185,0.31851,1.24848,0.81293,0.89887,0.0009241,0.0009241,0.0009241
+25,1846.59,1.19874,0.77357,0.90067,0.63342,0.48201,0.52219,0.32529,1.24313,0.8181,0.89801,0.0009208,0.0009208,0.0009208
+26,1920.33,1.18914,0.7634,0.89848,0.66484,0.46659,0.52273,0.32474,1.23604,0.81586,0.89809,0.0009175,0.0009175,0.0009175
+27,1994.05,1.19027,0.75791,0.8968,0.62291,0.486,0.52709,0.32505,1.2401,0.8138,0.89987,0.0009142,0.0009142,0.0009142
+28,2067.89,1.18943,0.75845,0.89546,0.62952,0.4772,0.52464,0.33019,1.23751,0.79594,0.89651,0.0009109,0.0009109,0.0009109
+29,2141.78,1.18853,0.75727,0.895,0.65237,0.47405,0.52411,0.32989,1.2226,0.79184,0.89237,0.0009076,0.0009076,0.0009076
+30,2215.44,1.18059,0.74204,0.89562,0.63721,0.47558,0.51775,0.32138,1.22581,0.80272,0.89263,0.0009043,0.0009043,0.0009043
+31,2289.23,1.17573,0.74725,0.89271,0.6468,0.47046,0.52153,0.32638,1.2288,0.79112,0.89563,0.000901,0.000901,0.000901
+32,2363.08,1.17888,0.74292,0.89287,0.66591,0.46519,0.52519,0.32722,1.22384,0.79058,0.89314,0.0008977,0.0008977,0.0008977
+33,2436.97,1.17005,0.73613,0.89263,0.64243,0.47902,0.52435,0.32877,1.21923,0.78505,0.89301,0.0008944,0.0008944,0.0008944
+34,2512.07,1.1632,0.72889,0.89069,0.64894,0.4685,0.51891,0.322,1.23532,0.80206,0.89608,0.0008911,0.0008911,0.0008911
+35,2587.17,1.16201,0.72743,0.88952,0.64691,0.46724,0.52403,0.32852,1.22295,0.79486,0.89299,0.0008878,0.0008878,0.0008878
+36,2660.64,1.16055,0.72498,0.8894,0.63265,0.48319,0.52265,0.32769,1.22537,0.79251,0.89651,0.0008845,0.0008845,0.0008845
+37,2735.17,1.15708,0.72049,0.8888,0.63683,0.4837,0.52562,0.33086,1.2182,0.77906,0.89215,0.0008812,0.0008812,0.0008812
+38,2809.44,1.16261,0.72399,0.88985,0.66075,0.47968,0.53176,0.33366,1.21256,0.77985,0.8892,0.0008779,0.0008779,0.0008779
+39,2883.14,1.158,0.71599,0.88784,0.63471,0.48871,0.52989,0.3319,1.21403,0.78409,0.8918,0.0008746,0.0008746,0.0008746
+40,2955.65,1.14864,0.70722,0.888,0.66291,0.48038,0.53138,0.33193,1.2104,0.77767,0.89061,0.0008713,0.0008713,0.0008713
+41,3028.11,1.14859,0.70842,0.88577,0.65266,0.47701,0.53123,0.33279,1.20868,0.7815,0.89215,0.000868,0.000868,0.000868
+42,3100.49,1.14499,0.70132,0.88634,0.65735,0.48205,0.52865,0.33116,1.21802,0.78321,0.89139,0.0008647,0.0008647,0.0008647
+43,3172.86,1.14437,0.70064,0.88572,0.65954,0.48343,0.53384,0.33578,1.20273,0.77706,0.88826,0.0008614,0.0008614,0.0008614
+44,3245.23,1.13991,0.69422,0.88404,0.65166,0.49156,0.53855,0.33644,1.21709,0.77893,0.89371,0.0008581,0.0008581,0.0008581
+45,3317.74,1.14372,0.69838,0.88459,0.64606,0.48434,0.53244,0.3329,1.2121,0.7753,0.89105,0.0008548,0.0008548,0.0008548
+46,3390.06,1.1414,0.69568,0.88466,0.63221,0.49846,0.53759,0.33808,1.20551,0.76904,0.88981,0.0008515,0.0008515,0.0008515
+47,3462.65,1.13173,0.68769,0.88171,0.65224,0.49405,0.54014,0.34013,1.19997,0.77476,0.88795,0.0008482,0.0008482,0.0008482
+48,3535.03,1.13729,0.68734,0.88423,0.66475,0.49016,0.53842,0.33647,1.20183,0.77463,0.88949,0.0008449,0.0008449,0.0008449
+49,3607.4,1.12732,0.68295,0.88225,0.64287,0.50616,0.54496,0.33972,1.20181,0.76998,0.88762,0.0008416,0.0008416,0.0008416
+50,3679.65,1.12769,0.67455,0.88072,0.64257,0.49628,0.53713,0.33665,1.19593,0.77052,0.88778,0.0008383,0.0008383,0.0008383
+51,3752.44,1.12459,0.67369,0.87994,0.66438,0.49439,0.54115,0.341,1.20121,0.76558,0.89086,0.000835,0.000835,0.000835
+52,3824.77,1.12492,0.67441,0.88148,0.64922,0.49792,0.54411,0.34039,1.20228,0.77638,0.8886,0.0008317,0.0008317,0.0008317
+53,3897.2,1.12367,0.66967,0.87916,0.67566,0.48504,0.5417,0.34078,1.19791,0.76749,0.88836,0.0008284,0.0008284,0.0008284
+54,3969.58,1.11978,0.6677,0.87803,0.65944,0.48818,0.53831,0.3412,1.20764,0.76303,0.89063,0.0008251,0.0008251,0.0008251
+55,4042,1.11091,0.65901,0.8786,0.66716,0.48986,0.54491,0.34139,1.1979,0.76396,0.8889,0.0008218,0.0008218,0.0008218
+56,4114.38,1.11294,0.65819,0.87891,0.65954,0.49612,0.54292,0.3413,1.19875,0.77262,0.88994,0.0008185,0.0008185,0.0008185
+57,4187.54,1.10293,0.65115,0.87574,0.66227,0.49126,0.54238,0.34046,1.19886,0.77201,0.88783,0.0008152,0.0008152,0.0008152
+58,4259.88,1.10904,0.65535,0.87706,0.66581,0.49197,0.54369,0.34109,1.19763,0.76306,0.89061,0.0008119,0.0008119,0.0008119
+59,4332.12,1.11256,0.65495,0.8777,0.67663,0.47929,0.53748,0.33687,1.19974,0.77325,0.88717,0.0008086,0.0008086,0.0008086
+60,4404.5,1.1163,0.65534,0.87849,0.6446,0.51004,0.54834,0.34649,1.19826,0.77172,0.8894,0.0008053,0.0008053,0.0008053
+61,4476.92,1.106,0.64779,0.87606,0.65811,0.4988,0.54471,0.34462,1.19408,0.76817,0.88797,0.000802,0.000802,0.000802
+62,4549.25,1.11071,0.65031,0.87666,0.64364,0.49678,0.53968,0.33836,1.20517,0.772,0.88932,0.0007987,0.0007987,0.0007987
+63,4621.53,1.10201,0.64659,0.87538,0.65773,0.49565,0.54188,0.34107,1.19662,0.76737,0.88941,0.0007954,0.0007954,0.0007954
+64,4694.02,1.1019,0.64234,0.87478,0.66535,0.49353,0.54393,0.34271,1.19865,0.78081,0.88816,0.0007921,0.0007921,0.0007921
+65,4766.38,1.0982,0.64241,0.87394,0.67216,0.49012,0.53965,0.33917,1.19457,0.77693,0.88879,0.0007888,0.0007888,0.0007888
+66,4838.58,1.09651,0.63617,0.8733,0.66479,0.49593,0.5458,0.34371,1.19311,0.76764,0.88848,0.0007855,0.0007855,0.0007855
+67,4911.39,1.09537,0.63411,0.87258,0.65958,0.49278,0.53976,0.33956,1.19891,0.77303,0.8899,0.0007822,0.0007822,0.0007822
+68,4983.7,1.09516,0.63298,0.87366,0.63835,0.50848,0.54478,0.34088,1.19916,0.77314,0.88865,0.0007789,0.0007789,0.0007789
+69,5055.91,1.0883,0.62911,0.87306,0.66238,0.4999,0.54766,0.34407,1.19216,0.76919,0.88575,0.0007756,0.0007756,0.0007756
+70,5128.17,1.08008,0.62228,0.87142,0.65797,0.50159,0.54531,0.34408,1.19755,0.76898,0.88762,0.0007723,0.0007723,0.0007723
+71,5200.48,1.09146,0.62682,0.87329,0.66136,0.5004,0.54511,0.34296,1.19562,0.76526,0.88845,0.000769,0.000769,0.000769
+72,5272.75,1.08888,0.62716,0.87175,0.66111,0.49765,0.5436,0.34159,1.19342,0.76764,0.88763,0.0007657,0.0007657,0.0007657
+73,5345.13,1.07556,0.61709,0.86945,0.65721,0.49722,0.54432,0.34278,1.19749,0.76871,0.88775,0.0007624,0.0007624,0.0007624
+74,5417.38,1.08477,0.6175,0.86957,0.65787,0.50006,0.54727,0.34465,1.19263,0.76693,0.8888,0.0007591,0.0007591,0.0007591
+75,5489.65,1.07628,0.61429,0.86938,0.65673,0.50398,0.5438,0.34317,1.20072,0.77864,0.8908,0.0007558,0.0007558,0.0007558
+76,5561.86,1.08551,0.62133,0.87045,0.64583,0.51014,0.5445,0.34393,1.19578,0.7748,0.88965,0.0007525,0.0007525,0.0007525
+77,5634.22,1.07656,0.61527,0.87059,0.66126,0.50183,0.54387,0.34368,1.19785,0.77115,0.88783,0.0007492,0.0007492,0.0007492
+78,5706.51,1.07227,0.60475,0.8687,0.65533,0.50521,0.5439,0.34286,1.19838,0.77319,0.89088,0.0007459,0.0007459,0.0007459
+79,5778.88,1.06573,0.60297,0.86757,0.66496,0.50694,0.54932,0.34623,1.19881,0.7633,0.89168,0.0007426,0.0007426,0.0007426
+80,5851.34,1.07305,0.61008,0.86604,0.64342,0.50819,0.546,0.3439,1.1967,0.76852,0.88934,0.0007393,0.0007393,0.0007393
+81,5923.65,1.06842,0.60472,0.86817,0.65509,0.50407,0.54473,0.3429,1.18831,0.77033,0.88778,0.000736,0.000736,0.000736
+82,5995.96,1.05868,0.59483,0.86755,0.64527,0.50256,0.54172,0.34184,1.19134,0.77004,0.88796,0.0007327,0.0007327,0.0007327
+83,6068.46,1.06946,0.60458,0.86802,0.65247,0.50126,0.54538,0.34521,1.19352,0.76936,0.88764,0.0007294,0.0007294,0.0007294
+84,6140.85,1.0633,0.59609,0.86778,0.66003,0.49853,0.54345,0.34426,1.19173,0.76804,0.88891,0.0007261,0.0007261,0.0007261
+85,6213.21,1.06255,0.59798,0.86686,0.64389,0.50609,0.53928,0.34,1.19596,0.78076,0.88901,0.0007228,0.0007228,0.0007228
+86,6285.59,1.05872,0.59551,0.86492,0.66053,0.49411,0.54097,0.3425,1.18957,0.77201,0.88797,0.0007195,0.0007195,0.0007195
+87,6357.89,1.06588,0.60055,0.86629,0.65764,0.50591,0.54331,0.34451,1.18845,0.76804,0.8894,0.0007162,0.0007162,0.0007162
+88,6430.13,1.05583,0.59233,0.86545,0.66929,0.49807,0.5432,0.34192,1.19021,0.76795,0.88885,0.0007129,0.0007129,0.0007129
+89,6502.44,1.05788,0.59212,0.86488,0.65811,0.50078,0.54185,0.33991,1.18722,0.76635,0.88794,0.0007096,0.0007096,0.0007096
+90,6574.82,1.06001,0.59024,0.86442,0.65954,0.4991,0.5409,0.34017,1.19106,0.76648,0.88913,0.0007063,0.0007063,0.0007063
+91,6647.18,1.05431,0.58916,0.86293,0.65832,0.49574,0.54238,0.34164,1.19167,0.77427,0.88956,0.000703,0.000703,0.000703
+92,6719.49,1.05512,0.58783,0.86384,0.66736,0.49951,0.54549,0.34382,1.19155,0.77794,0.88943,0.0006997,0.0006997,0.0006997
+93,6791.88,1.0574,0.58857,0.86407,0.658,0.50624,0.54582,0.34334,1.1921,0.77577,0.89028,0.0006964,0.0006964,0.0006964
+94,6864.22,1.04456,0.58057,0.86156,0.67277,0.49883,0.54728,0.34536,1.19149,0.77641,0.88997,0.0006931,0.0006931,0.0006931
+95,6936.57,1.03756,0.57759,0.86071,0.65774,0.5049,0.54407,0.34391,1.19252,0.77677,0.89113,0.0006898,0.0006898,0.0006898
+96,7008.71,1.0463,0.58003,0.86268,0.64992,0.50999,0.54584,0.34515,1.19362,0.77831,0.89113,0.0006865,0.0006865,0.0006865
+97,7081.06,1.0451,0.57911,0.86158,0.66347,0.50119,0.54566,0.34544,1.18953,0.77758,0.88891,0.0006832,0.0006832,0.0006832
+98,7153.43,1.04041,0.57505,0.86344,0.66747,0.49646,0.54544,0.34505,1.18929,0.77578,0.88913,0.0006799,0.0006799,0.0006799
+99,7225.84,1.0414,0.57453,0.86095,0.66874,0.49732,0.54594,0.3456,1.18851,0.77512,0.8899,0.0006766,0.0006766,0.0006766
+100,7298.73,1.03886,0.57283,0.86126,0.66191,0.49803,0.54386,0.34598,1.1903,0.78002,0.89023,0.0006733,0.0006733,0.0006733

vis6class_exp/vis6class_v8m/6class2/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/vis6class_exp/vis6class.yaml
+epochs: 600
+time: null
+patience: 100
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: vis6class_v8m
+name: 6class2
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/vis6class_exp/vis6class_v8m/6class2

vis6class_exp/vis6class_v8m/6class2/results.csv

@@ -0,0 +1,187 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,72.737,1.45177,1.3499,0.97119,0.48954,0.30681,0.30529,0.17932,1.46069,1.21004,0.94941,0.0671728,0.000331588,0.000331588
+2,145.259,1.41643,1.09937,0.95936,0.51569,0.348,0.36711,0.21975,1.40953,1.04933,0.9344,0.0341717,0.000663824,0.000663824
+3,217.511,1.39519,1.03755,0.94925,0.53215,0.35639,0.37598,0.22147,1.4217,1.01354,0.94558,0.00116948,0.000994961,0.000994961
+4,290.096,1.38565,1.0174,0.94712,0.53937,0.37549,0.39881,0.23714,1.40609,1.01564,0.93907,0.00099505,0.00099505,0.00099505
+5,362.608,1.35601,0.97607,0.94142,0.54992,0.39999,0.4189,0.25481,1.364,0.96776,0.9313,0.0009934,0.0009934,0.0009934
+6,435.063,1.32156,0.93836,0.93301,0.55129,0.41798,0.44074,0.267,1.33671,0.93321,0.92151,0.00099175,0.00099175,0.00099175
+7,507.477,1.31513,0.92741,0.92914,0.56997,0.41232,0.44804,0.26913,1.33529,0.91844,0.92161,0.0009901,0.0009901,0.0009901
+8,579.866,1.30385,0.91348,0.9277,0.59221,0.41174,0.44511,0.26816,1.3207,0.89299,0.91879,0.00098845,0.00098845,0.00098845
+9,652.3,1.29593,0.89772,0.92379,0.57481,0.44673,0.47319,0.28947,1.29252,0.91278,0.91245,0.0009868,0.0009868,0.0009868
+10,724.753,1.2773,0.88313,0.92125,0.56154,0.43174,0.45954,0.27926,1.32213,0.89067,0.91499,0.00098515,0.00098515,0.00098515
+11,797.108,1.26686,0.86462,0.91826,0.59164,0.414,0.45505,0.27925,1.32693,0.9093,0.91792,0.0009835,0.0009835,0.0009835
+12,869.466,1.26241,0.8635,0.91615,0.59304,0.44577,0.4814,0.2946,1.28946,0.86411,0.91064,0.00098185,0.00098185,0.00098185
+13,941.916,1.25849,0.8488,0.9133,0.59279,0.45301,0.48149,0.29445,1.30078,0.86615,0.90923,0.0009802,0.0009802,0.0009802
+14,1014.13,1.25146,0.84592,0.91302,0.60702,0.46152,0.49562,0.30434,1.28529,0.8501,0.90949,0.00097855,0.00097855,0.00097855
+15,1086.57,1.2433,0.82949,0.90907,0.61154,0.45736,0.49543,0.30455,1.27646,0.84349,0.90697,0.0009769,0.0009769,0.0009769
+16,1158.96,1.23719,0.8262,0.90884,0.60868,0.45495,0.49393,0.30246,1.2691,0.83582,0.9009,0.00097525,0.00097525,0.00097525
+17,1231.28,1.23246,0.82207,0.90773,0.61176,0.46142,0.50004,0.30986,1.25366,0.84857,0.90132,0.0009736,0.0009736,0.0009736
+18,1303.62,1.23402,0.81355,0.9065,0.62448,0.458,0.49844,0.31222,1.25743,0.82516,0.89927,0.00097195,0.00097195,0.00097195
+19,1376,1.21622,0.80395,0.90508,0.60854,0.46524,0.50922,0.31668,1.26839,0.83097,0.9038,0.0009703,0.0009703,0.0009703
+20,1448.27,1.21996,0.79983,0.90519,0.60858,0.47148,0.50558,0.31409,1.25818,0.82764,0.90293,0.00096865,0.00096865,0.00096865
+21,1520.61,1.22322,0.80093,0.9052,0.64455,0.46105,0.50956,0.31452,1.25627,0.83241,0.9029,0.000967,0.000967,0.000967
+22,1593.02,1.20371,0.78634,0.90081,0.59679,0.45568,0.4922,0.30748,1.2614,0.83745,0.90051,0.00096535,0.00096535,0.00096535
+23,1665.36,1.20261,0.7808,0.90082,0.63045,0.4775,0.51558,0.32076,1.25094,0.81355,0.89995,0.0009637,0.0009637,0.0009637
+24,1737.64,1.19467,0.77229,0.89903,0.62333,0.46517,0.50437,0.31446,1.23966,0.81092,0.90075,0.00096205,0.00096205,0.00096205
+25,1810.04,1.19834,0.77569,0.90157,0.63327,0.47282,0.5167,0.32484,1.24061,0.82096,0.89414,0.0009604,0.0009604,0.0009604
+26,1882.36,1.19423,0.76706,0.90021,0.63337,0.46873,0.52114,0.32483,1.23635,0.81724,0.89706,0.00095875,0.00095875,0.00095875
+27,1954.69,1.19284,0.76055,0.89767,0.63242,0.48032,0.52245,0.3258,1.25015,0.8098,0.90155,0.0009571,0.0009571,0.0009571
+28,2027.05,1.19259,0.76047,0.896,0.62508,0.47202,0.51627,0.32041,1.25853,0.81012,0.90283,0.00095545,0.00095545,0.00095545
+29,2099.39,1.19025,0.75798,0.89554,0.64925,0.48362,0.53221,0.33325,1.22656,0.8042,0.89485,0.0009538,0.0009538,0.0009538
+30,2171.61,1.18241,0.74459,0.89648,0.64479,0.48298,0.52818,0.3286,1.22912,0.79349,0.89775,0.00095215,0.00095215,0.00095215
+31,2243.86,1.17875,0.75268,0.89338,0.64261,0.4879,0.53199,0.33534,1.22343,0.79848,0.89628,0.0009505,0.0009505,0.0009505
+32,2316.19,1.18473,0.75119,0.89432,0.62964,0.48815,0.52537,0.32652,1.22146,0.80032,0.89288,0.00094885,0.00094885,0.00094885
+33,2388.56,1.17415,0.74142,0.89419,0.65025,0.47264,0.52712,0.32948,1.22089,0.78761,0.89377,0.0009472,0.0009472,0.0009472
+34,2460.92,1.16609,0.73147,0.89178,0.6414,0.47677,0.52358,0.32527,1.22078,0.79837,0.8932,0.00094555,0.00094555,0.00094555
+35,2533.91,1.16549,0.73254,0.89103,0.64599,0.48047,0.52853,0.32827,1.2239,0.78803,0.89588,0.0009439,0.0009439,0.0009439
+36,2608.02,1.1644,0.73027,0.89064,0.64509,0.48353,0.53129,0.33218,1.21224,0.78572,0.89136,0.00094225,0.00094225,0.00094225
+37,2681.66,1.16125,0.7269,0.88967,0.65259,0.4918,0.53473,0.33366,1.21601,0.78924,0.89365,0.0009406,0.0009406,0.0009406
+38,2754,1.16903,0.73047,0.89189,0.66162,0.48744,0.53717,0.33566,1.21969,0.78049,0.89523,0.00093895,0.00093895,0.00093895
+39,2826.34,1.16142,0.71879,0.88806,0.6421,0.48384,0.52918,0.33237,1.21605,0.79474,0.89238,0.0009373,0.0009373,0.0009373
+40,2898.6,1.15578,0.71459,0.88879,0.65262,0.49704,0.54023,0.34085,1.21222,0.7766,0.894,0.00093565,0.00093565,0.00093565
+41,2971.03,1.15058,0.71198,0.88627,0.64881,0.49684,0.5465,0.34272,1.21169,0.77826,0.89543,0.000934,0.000934,0.000934
+42,3043.4,1.15016,0.70886,0.88804,0.66036,0.49255,0.54224,0.3392,1.21453,0.77956,0.89251,0.00093235,0.00093235,0.00093235
+43,3115.8,1.14813,0.70686,0.88723,0.64109,0.50083,0.54222,0.34065,1.20817,0.77646,0.88969,0.0009307,0.0009307,0.0009307
+44,3188.07,1.1452,0.70293,0.88504,0.65725,0.49637,0.53884,0.33921,1.21544,0.77561,0.89433,0.00092905,0.00092905,0.00092905
+45,3260.45,1.14926,0.70372,0.88566,0.65689,0.4884,0.53707,0.3368,1.21143,0.77677,0.89118,0.0009274,0.0009274,0.0009274
+46,3332.69,1.14623,0.7,0.88575,0.66543,0.48589,0.53812,0.33877,1.21676,0.77225,0.8931,0.00092575,0.00092575,0.00092575
+47,3405.23,1.13626,0.69402,0.88284,0.65806,0.49123,0.54479,0.34009,1.20989,0.78151,0.89305,0.0009241,0.0009241,0.0009241
+48,3477.59,1.14177,0.69621,0.88564,0.6595,0.49283,0.54478,0.34213,1.20568,0.78292,0.89117,0.00092245,0.00092245,0.00092245
+49,3549.97,1.13236,0.68789,0.88352,0.66013,0.48967,0.53958,0.33687,1.21342,0.7733,0.89422,0.0009208,0.0009208,0.0009208
+50,3622.23,1.13373,0.6825,0.88151,0.66861,0.49138,0.5436,0.34066,1.21085,0.7781,0.89259,0.00091915,0.00091915,0.00091915
+51,3694.9,1.12987,0.68214,0.88055,0.64976,0.50479,0.54459,0.34273,1.20041,0.76117,0.88906,0.0009175,0.0009175,0.0009175
+52,3769.1,1.12952,0.68015,0.88236,0.67014,0.49388,0.54785,0.34431,1.20305,0.76721,0.89067,0.00091585,0.00091585,0.00091585
+53,3845.24,1.12818,0.67503,0.88015,0.65329,0.50391,0.54998,0.34518,1.20071,0.77044,0.88734,0.0009142,0.0009142,0.0009142
+54,3920.19,1.12539,0.67421,0.87931,0.67196,0.48386,0.54301,0.34231,1.19752,0.77885,0.88972,0.00091255,0.00091255,0.00091255
+55,3993.34,1.11628,0.66518,0.87976,0.67265,0.50073,0.55034,0.34705,1.19835,0.7641,0.88766,0.0009109,0.0009109,0.0009109
+56,4065.6,1.11883,0.66422,0.88026,0.66827,0.486,0.54042,0.34098,1.19894,0.77048,0.89036,0.00090925,0.00090925,0.00090925
+57,4138.08,1.10893,0.65857,0.87715,0.65354,0.49715,0.54175,0.34216,1.20237,0.77624,0.88906,0.0009076,0.0009076,0.0009076
+58,4210.32,1.11571,0.66504,0.87863,0.65137,0.49786,0.54437,0.3412,1.19606,0.76897,0.88918,0.00090595,0.00090595,0.00090595
+59,4282.52,1.11779,0.66166,0.87904,0.64097,0.50391,0.5457,0.34429,1.19209,0.76886,0.88617,0.0009043,0.0009043,0.0009043
+60,4354.8,1.12066,0.6612,0.87997,0.66987,0.4985,0.54409,0.34318,1.20218,0.77232,0.88938,0.00090265,0.00090265,0.00090265
+61,4427.07,1.11248,0.65849,0.87838,0.67474,0.49368,0.54656,0.34726,1.19442,0.77499,0.88719,0.000901,0.000901,0.000901
+62,4499.42,1.11531,0.65582,0.87789,0.68688,0.491,0.54705,0.34517,1.2005,0.76907,0.88667,0.00089935,0.00089935,0.00089935
+63,4571.81,1.10904,0.65513,0.87686,0.67222,0.4951,0.54598,0.34407,1.19771,0.77059,0.88897,0.0008977,0.0008977,0.0008977
+64,4644.23,1.10843,0.65289,0.87677,0.67669,0.48893,0.54573,0.34342,1.19382,0.7693,0.88624,0.00089605,0.00089605,0.00089605
+65,4716.54,1.10467,0.65013,0.87612,0.66774,0.4941,0.54817,0.34721,1.1961,0.76173,0.88791,0.0008944,0.0008944,0.0008944
+66,4788.72,1.10409,0.64634,0.87544,0.64695,0.50827,0.54607,0.34572,1.19439,0.76959,0.88871,0.00089275,0.00089275,0.00089275
+67,4861.12,1.10075,0.63885,0.87408,0.6651,0.50159,0.54995,0.34507,1.19862,0.77373,0.88935,0.0008911,0.0008911,0.0008911
+68,4933.53,1.10218,0.63962,0.87535,0.66654,0.50152,0.54928,0.34517,1.19865,0.77508,0.88987,0.00088945,0.00088945,0.00088945
+69,5005.94,1.09538,0.6366,0.87412,0.67059,0.50131,0.55087,0.34788,1.19825,0.76778,0.89022,0.0008878,0.0008878,0.0008878
+70,5078.4,1.08488,0.6294,0.87246,0.64927,0.50679,0.55076,0.34633,1.19907,0.77485,0.88867,0.00088615,0.00088615,0.00088615
+71,5150.79,1.09718,0.6346,0.87436,0.65603,0.50543,0.54586,0.34482,1.20113,0.77295,0.88899,0.0008845,0.0008845,0.0008845
+72,5223.31,1.09698,0.63752,0.87336,0.67832,0.49065,0.54774,0.34549,1.19276,0.76489,0.88706,0.00088285,0.00088285,0.00088285
+73,5295.86,1.08718,0.62772,0.87311,0.66895,0.50115,0.55087,0.34903,1.19536,0.76795,0.88953,0.0008812,0.0008812,0.0008812
+74,5368.31,1.09173,0.62591,0.87142,0.65321,0.50049,0.54909,0.346,1.19257,0.77368,0.88797,0.00087955,0.00087955,0.00087955
+75,5440.71,1.08386,0.62446,0.8713,0.66003,0.50506,0.55198,0.34786,1.18925,0.7653,0.8862,0.0008779,0.0008779,0.0008779
+76,5513.13,1.09068,0.62616,0.87191,0.67411,0.49852,0.54843,0.34741,1.18911,0.77415,0.8881,0.00087625,0.00087625,0.00087625
+77,5585.59,1.08116,0.6205,0.87149,0.66281,0.50779,0.5503,0.34646,1.19151,0.7642,0.8886,0.0008746,0.0008746,0.0008746
+78,5658.01,1.0815,0.61432,0.87114,0.67578,0.49892,0.54563,0.34599,1.19142,0.76895,0.88728,0.00087295,0.00087295,0.00087295
+79,5730.6,1.07114,0.60869,0.86868,0.65774,0.50059,0.54476,0.34497,1.19638,0.76712,0.8891,0.0008713,0.0008713,0.0008713
+80,5803.04,1.08027,0.61861,0.86776,0.66866,0.50061,0.54707,0.34764,1.18702,0.77129,0.88689,0.00086965,0.00086965,0.00086965
+81,5875.4,1.07542,0.61253,0.86973,0.65263,0.51314,0.54969,0.34847,1.18886,0.77443,0.8863,0.000868,0.000868,0.000868
+82,5947.92,1.06649,0.60695,0.86941,0.67022,0.49905,0.54703,0.34807,1.18915,0.77419,0.8855,0.00086635,0.00086635,0.00086635
+83,6020.55,1.07665,0.61223,0.86915,0.65365,0.51121,0.55139,0.34838,1.19204,0.76962,0.88737,0.0008647,0.0008647,0.0008647
+84,6093.04,1.07314,0.60612,0.86995,0.65331,0.5057,0.5475,0.34768,1.18985,0.77056,0.8878,0.00086305,0.00086305,0.00086305
+85,6165.48,1.06819,0.60353,0.86834,0.6713,0.50264,0.54946,0.34815,1.19171,0.77758,0.88834,0.0008614,0.0008614,0.0008614
+86,6237.95,1.06621,0.60231,0.86677,0.65965,0.5109,0.55417,0.35043,1.18916,0.77287,0.88672,0.00085975,0.00085975,0.00085975
+87,6310.36,1.07447,0.60976,0.86829,0.66464,0.50481,0.55104,0.34944,1.19461,0.77689,0.88772,0.0008581,0.0008581,0.0008581
+88,6382.69,1.06577,0.60213,0.86709,0.6699,0.49989,0.54979,0.3485,1.19404,0.78195,0.88725,0.00085645,0.00085645,0.00085645
+89,6455.07,1.06648,0.60041,0.86731,0.66336,0.50623,0.54905,0.34826,1.19608,0.78134,0.88844,0.0008548,0.0008548,0.0008548
+90,6527.56,1.06808,0.59934,0.86625,0.68432,0.49654,0.55111,0.34984,1.18522,0.77544,0.88508,0.00085315,0.00085315,0.00085315
+91,6600.01,1.06304,0.5972,0.86442,0.66921,0.50346,0.55062,0.34804,1.19016,0.78142,0.88589,0.0008515,0.0008515,0.0008515
+92,6672.42,1.06414,0.59905,0.8658,0.66221,0.50413,0.55059,0.34846,1.18953,0.78374,0.88744,0.00084985,0.00084985,0.00084985
+93,6744.94,1.06828,0.59974,0.86645,0.66419,0.50561,0.54935,0.34757,1.18712,0.78315,0.88785,0.0008482,0.0008482,0.0008482
+94,6817.45,1.05625,0.59019,0.86313,0.67126,0.49933,0.54701,0.34703,1.19233,0.78203,0.88718,0.00084655,0.00084655,0.00084655
+95,6889.91,1.04605,0.58626,0.86262,0.66929,0.50333,0.54935,0.3485,1.1965,0.78294,0.88792,0.0008449,0.0008449,0.0008449
+96,6962.23,1.05671,0.58926,0.86558,0.66283,0.50822,0.54891,0.34689,1.19646,0.78104,0.88824,0.00084325,0.00084325,0.00084325
+97,7034.75,1.05632,0.5896,0.86455,0.66684,0.50376,0.54826,0.34849,1.18844,0.77599,0.88548,0.0008416,0.0008416,0.0008416
+98,7107.18,1.05158,0.58572,0.86638,0.66431,0.50762,0.55083,0.34833,1.18448,0.78099,0.88612,0.00083995,0.00083995,0.00083995
+99,7179.65,1.05229,0.58653,0.86332,0.6671,0.50746,0.55297,0.34899,1.18526,0.77791,0.88599,0.0008383,0.0008383,0.0008383
+100,7252.18,1.04745,0.58254,0.86341,0.6789,0.50191,0.55198,0.34949,1.1881,0.78241,0.88599,0.00083665,0.00083665,0.00083665
+101,7324.67,1.04421,0.58074,0.86384,0.66999,0.50648,0.55072,0.34794,1.18697,0.78611,0.88511,0.000835,0.000835,0.000835
+102,7397,1.04692,0.58175,0.86325,0.67008,0.50553,0.55281,0.35031,1.18542,0.7825,0.885,0.00083335,0.00083335,0.00083335
+103,7469.41,1.03982,0.57844,0.86101,0.66417,0.50691,0.55275,0.34957,1.18627,0.7823,0.88571,0.0008317,0.0008317,0.0008317
+104,7541.86,1.04371,0.57491,0.86185,0.67503,0.50189,0.55202,0.34997,1.18967,0.78245,0.88551,0.00083005,0.00083005,0.00083005
+105,7614.23,1.04597,0.57929,0.86255,0.6553,0.50965,0.5512,0.34857,1.18904,0.78275,0.88577,0.0008284,0.0008284,0.0008284
+106,7686.71,1.04398,0.5786,0.86113,0.666,0.50359,0.55039,0.34883,1.18945,0.78219,0.88613,0.00082675,0.00082675,0.00082675
+107,7759.27,1.04157,0.57522,0.86366,0.67416,0.50087,0.55146,0.34924,1.18721,0.77777,0.88542,0.0008251,0.0008251,0.0008251
+108,7831.72,1.03951,0.57104,0.86047,0.67089,0.50358,0.55214,0.34892,1.1871,0.77592,0.88528,0.00082345,0.00082345,0.00082345
+109,7904.2,1.03631,0.57295,0.86018,0.66284,0.50727,0.5502,0.34795,1.18772,0.78101,0.88523,0.0008218,0.0008218,0.0008218
+110,7976.72,1.0321,0.5684,0.85976,0.66292,0.51125,0.5504,0.34829,1.18671,0.78361,0.88566,0.00082015,0.00082015,0.00082015
+111,8049.11,1.04522,0.57368,0.86045,0.6647,0.50954,0.54928,0.34725,1.18904,0.78506,0.88617,0.0008185,0.0008185,0.0008185
+112,8121.54,1.02903,0.56446,0.85918,0.66793,0.50688,0.54791,0.34675,1.19012,0.786,0.88579,0.00081685,0.00081685,0.00081685
+113,8194.08,1.02992,0.56434,0.85783,0.66144,0.50789,0.54764,0.34639,1.18969,0.78753,0.88629,0.0008152,0.0008152,0.0008152
+114,8266.62,1.03075,0.56575,0.85941,0.65667,0.50994,0.54795,0.34654,1.19041,0.78414,0.88658,0.00081355,0.00081355,0.00081355
+115,8339.19,1.02835,0.5644,0.8574,0.66666,0.50552,0.54735,0.3464,1.19119,0.78495,0.88599,0.0008119,0.0008119,0.0008119
+116,8411.56,1.01978,0.55888,0.85873,0.66621,0.50761,0.54764,0.34703,1.19046,0.7865,0.88624,0.00081025,0.00081025,0.00081025
+117,8484.1,1.02243,0.55955,0.85711,0.66755,0.50739,0.5477,0.34661,1.18868,0.78558,0.88634,0.0008086,0.0008086,0.0008086
+118,8556.47,1.03104,0.56307,0.85839,0.66031,0.50842,0.54797,0.34704,1.188,0.78695,0.88656,0.00080695,0.00080695,0.00080695
+119,8628.94,1.02169,0.55988,0.85775,0.6638,0.50555,0.54891,0.34744,1.18641,0.78644,0.88657,0.0008053,0.0008053,0.0008053
+120,8701.44,1.02222,0.55843,0.85909,0.66898,0.50549,0.54784,0.34679,1.18874,0.7846,0.88729,0.00080365,0.00080365,0.00080365
+121,8774.03,1.02254,0.55752,0.85708,0.67184,0.50251,0.54705,0.34677,1.18981,0.7854,0.88731,0.000802,0.000802,0.000802
+122,8846.42,1.0239,0.55665,0.85775,0.67363,0.5018,0.54646,0.34543,1.19008,0.78554,0.88703,0.00080035,0.00080035,0.00080035
+123,8918.78,1.02307,0.55869,0.85649,0.67682,0.50052,0.54602,0.34592,1.19072,0.7843,0.88743,0.0007987,0.0007987,0.0007987
+124,8991.22,1.01487,0.55568,0.8563,0.67618,0.50111,0.54642,0.34543,1.19118,0.78519,0.88792,0.00079705,0.00079705,0.00079705
+125,9063.57,1.01955,0.55719,0.85778,0.67354,0.50214,0.54602,0.34509,1.19089,0.78494,0.88826,0.0007954,0.0007954,0.0007954
+126,9136.06,1.02061,0.55542,0.85773,0.6729,0.50007,0.54638,0.34589,1.19074,0.78673,0.88782,0.00079375,0.00079375,0.00079375
+127,9208.59,1.01356,0.54978,0.85547,0.67228,0.50148,0.54631,0.34622,1.1893,0.78797,0.88756,0.0007921,0.0007921,0.0007921
+128,9280.96,1.01064,0.54896,0.8559,0.66366,0.50874,0.54766,0.34665,1.18891,0.78686,0.88707,0.00079045,0.00079045,0.00079045
+129,9353.4,1.01602,0.55393,0.85588,0.65911,0.51045,0.54755,0.34622,1.18735,0.78552,0.8869,0.0007888,0.0007888,0.0007888
+130,9425.82,1.00902,0.54897,0.85418,0.666,0.50742,0.54779,0.34639,1.18783,0.78486,0.88703,0.00078715,0.00078715,0.00078715
+131,9498.38,1.01303,0.54922,0.85326,0.67766,0.49972,0.54754,0.34626,1.18791,0.78449,0.88679,0.0007855,0.0007855,0.0007855
+132,9570.79,1.00704,0.54679,0.85556,0.67253,0.50363,0.54785,0.34681,1.18843,0.78508,0.88681,0.00078385,0.00078385,0.00078385
+133,9643.3,1.0056,0.54446,0.85402,0.67008,0.50449,0.54796,0.34688,1.18859,0.78452,0.88676,0.0007822,0.0007822,0.0007822
+134,9715.76,1.00696,0.54671,0.85444,0.67414,0.50404,0.54867,0.34642,1.18809,0.78589,0.88692,0.00078055,0.00078055,0.00078055
+135,9788.2,1.0064,0.54299,0.85367,0.67565,0.50396,0.54783,0.34638,1.18842,0.78707,0.88758,0.0007789,0.0007789,0.0007789
+136,9860.68,1.00381,0.54353,0.85369,0.6727,0.50639,0.5463,0.34641,1.18911,0.78648,0.88774,0.00077725,0.00077725,0.00077725
+137,9933.08,1.00401,0.54291,0.85244,0.666,0.51047,0.54611,0.34621,1.18956,0.78679,0.88803,0.0007756,0.0007756,0.0007756
+138,10005.6,1.00042,0.54213,0.85324,0.66882,0.50844,0.54698,0.34702,1.18966,0.78559,0.88815,0.00077395,0.00077395,0.00077395
+139,10078.1,1.00312,0.54261,0.85251,0.66976,0.50651,0.54677,0.34734,1.19042,0.78425,0.8887,0.0007723,0.0007723,0.0007723
+140,10150.5,1.00054,0.53983,0.85356,0.67176,0.50674,0.54808,0.34774,1.19207,0.78421,0.88932,0.00077065,0.00077065,0.00077065
+141,10222.9,0.99637,0.53862,0.85336,0.67533,0.50703,0.54871,0.34831,1.19182,0.78425,0.88911,0.000769,0.000769,0.000769
+142,10295.4,0.99712,0.53591,0.85239,0.67619,0.50661,0.54881,0.34865,1.1917,0.78417,0.88862,0.00076735,0.00076735,0.00076735
+143,10368,0.99763,0.53804,0.85085,0.67451,0.50728,0.54913,0.34842,1.1913,0.7844,0.88852,0.0007657,0.0007657,0.0007657
+144,10440.5,0.99905,0.54047,0.85247,0.66851,0.51014,0.54896,0.34842,1.1907,0.78519,0.88855,0.00076405,0.00076405,0.00076405
+145,10512.9,0.99816,0.53857,0.8524,0.66142,0.51457,0.54901,0.34881,1.19059,0.78766,0.88838,0.0007624,0.0007624,0.0007624
+146,10585.5,1.00019,0.54106,0.85295,0.66344,0.50904,0.54875,0.34906,1.19109,0.78768,0.88819,0.00076075,0.00076075,0.00076075
+147,10658,0.99693,0.53674,0.85209,0.66666,0.50948,0.54895,0.3493,1.18967,0.78689,0.88798,0.0007591,0.0007591,0.0007591
+148,10730.4,0.99241,0.53463,0.85142,0.66763,0.50781,0.5486,0.34908,1.19034,0.78767,0.8883,0.00075745,0.00075745,0.00075745
+149,10802.9,1.00106,0.53681,0.85242,0.65939,0.51222,0.54899,0.34922,1.19045,0.78775,0.8883,0.0007558,0.0007558,0.0007558
+150,10875.3,0.9881,0.52889,0.85046,0.66222,0.51291,0.5489,0.34956,1.19073,0.78744,0.8883,0.00075415,0.00075415,0.00075415
+151,10947.8,0.99636,0.53499,0.8503,0.66432,0.51159,0.54878,0.34942,1.19082,0.78792,0.88841,0.0007525,0.0007525,0.0007525
+152,11020.4,0.98805,0.52658,0.84947,0.66569,0.51068,0.54909,0.34954,1.19173,0.78772,0.88873,0.00075085,0.00075085,0.00075085
+153,11092.9,0.98996,0.5288,0.85036,0.66541,0.50968,0.54912,0.34931,1.19185,0.78791,0.88897,0.0007492,0.0007492,0.0007492
+154,11165.3,0.97409,0.51963,0.84792,0.66391,0.50984,0.54895,0.34952,1.1924,0.78811,0.88889,0.00074755,0.00074755,0.00074755
+155,11237.8,0.99204,0.53211,0.84892,0.66625,0.50848,0.54913,0.34946,1.19204,0.78816,0.88902,0.0007459,0.0007459,0.0007459
+156,11310.4,0.98509,0.52689,0.84924,0.66405,0.51149,0.54916,0.34911,1.19231,0.78956,0.8891,0.00074425,0.00074425,0.00074425
+157,11382.7,0.9873,0.52701,0.85052,0.6693,0.50888,0.54924,0.34926,1.19219,0.78972,0.88914,0.0007426,0.0007426,0.0007426
+158,11455.2,0.98402,0.52789,0.84837,0.66936,0.50993,0.54938,0.34948,1.19207,0.78941,0.8893,0.00074095,0.00074095,0.00074095
+159,11527.8,0.98178,0.52533,0.849,0.66781,0.51034,0.54917,0.34915,1.19219,0.78974,0.88941,0.0007393,0.0007393,0.0007393
+160,11600.2,0.98086,0.52384,0.84882,0.66549,0.51197,0.54901,0.34954,1.19206,0.78933,0.88931,0.00073765,0.00073765,0.00073765
+161,11672.7,0.98053,0.52369,0.84896,0.67099,0.51082,0.54982,0.34951,1.19141,0.78863,0.88924,0.000736,0.000736,0.000736
+162,11745.2,0.97465,0.52035,0.84683,0.66802,0.51244,0.54945,0.34957,1.1915,0.78912,0.8891,0.00073435,0.00073435,0.00073435
+163,11817.8,0.98263,0.52287,0.84781,0.67022,0.51189,0.54947,0.3496,1.19144,0.79003,0.88916,0.0007327,0.0007327,0.0007327
+164,11890.2,0.97093,0.51706,0.84904,0.6667,0.51444,0.54973,0.3496,1.19176,0.78995,0.88938,0.00073105,0.00073105,0.00073105
+165,11962.6,0.97387,0.51707,0.84878,0.66649,0.51356,0.54934,0.34921,1.19142,0.79069,0.88964,0.0007294,0.0007294,0.0007294
+166,12035,0.97158,0.51715,0.84706,0.66408,0.51577,0.54935,0.34929,1.19151,0.79211,0.88975,0.00072775,0.00072775,0.00072775
+167,12107.4,0.96969,0.51756,0.84623,0.66243,0.51491,0.54937,0.34926,1.19108,0.79261,0.88979,0.0007261,0.0007261,0.0007261
+168,12179.7,0.97492,0.52131,0.84708,0.65798,0.51608,0.54866,0.34894,1.19118,0.79303,0.88974,0.00072445,0.00072445,0.00072445
+169,12252.1,0.96656,0.51485,0.84465,0.65886,0.5165,0.54871,0.34894,1.19131,0.794,0.88985,0.0007228,0.0007228,0.0007228
+170,12324.3,0.97422,0.51749,0.8488,0.65565,0.51773,0.54872,0.34858,1.19165,0.79394,0.88991,0.00072115,0.00072115,0.00072115
+171,12396.7,0.96957,0.51808,0.84868,0.65653,0.51837,0.54889,0.34844,1.19213,0.79433,0.89001,0.0007195,0.0007195,0.0007195
+172,12469.2,0.96935,0.51438,0.84538,0.65765,0.51836,0.549,0.34826,1.19172,0.79536,0.89,0.00071785,0.00071785,0.00071785
+173,12541.6,0.97113,0.5194,0.84726,0.65638,0.51899,0.54894,0.34851,1.19239,0.79557,0.89007,0.0007162,0.0007162,0.0007162
+174,12614,0.97074,0.51705,0.8473,0.65649,0.51758,0.54895,0.34835,1.19273,0.79571,0.8902,0.00071455,0.00071455,0.00071455
+175,12686.4,0.96092,0.51021,0.84402,0.65739,0.517,0.54871,0.34865,1.19303,0.79583,0.89037,0.0007129,0.0007129,0.0007129
+176,12758.9,0.96361,0.50986,0.84593,0.65533,0.51628,0.5486,0.34823,1.19266,0.79628,0.89038,0.00071125,0.00071125,0.00071125
+177,12831.2,0.96305,0.51156,0.84572,0.65771,0.51455,0.54867,0.34846,1.19266,0.7964,0.89035,0.0007096,0.0007096,0.0007096
+178,12903.7,0.96548,0.51648,0.84695,0.6566,0.51506,0.54853,0.34811,1.19251,0.79628,0.89031,0.00070795,0.00070795,0.00070795
+179,12976.2,0.96977,0.51527,0.84652,0.65736,0.51312,0.54842,0.34797,1.19256,0.79713,0.89019,0.0007063,0.0007063,0.0007063
+180,13048.7,0.968,0.51154,0.84488,0.65724,0.51276,0.54798,0.34791,1.19222,0.79745,0.89,0.00070465,0.00070465,0.00070465
+181,13121.2,0.96426,0.51003,0.8444,0.65641,0.51402,0.54828,0.34772,1.19231,0.79678,0.88996,0.000703,0.000703,0.000703
+182,13193.7,0.96249,0.5106,0.84503,0.65582,0.51342,0.54805,0.34761,1.1923,0.79708,0.89005,0.00070135,0.00070135,0.00070135
+183,13266.2,0.95701,0.50576,0.84421,0.65401,0.51605,0.5479,0.34767,1.19241,0.79742,0.89001,0.0006997,0.0006997,0.0006997
+184,13338.7,0.95766,0.50939,0.84378,0.65337,0.5165,0.54811,0.34764,1.19268,0.79783,0.89003,0.00069805,0.00069805,0.00069805
+185,13411.1,0.96173,0.50975,0.84391,0.65658,0.51541,0.5479,0.34748,1.19282,0.79808,0.88989,0.0006964,0.0006964,0.0006964
+186,13483.6,0.95881,0.50771,0.84393,0.6541,0.51585,0.54788,0.3476,1.19337,0.79828,0.89004,0.00069475,0.00069475,0.00069475

vis6class_exp/vis6class_v8m/6class_final/args.yaml

@@ -0,0 +1,106 @@
+task: detect
+mode: train
+model: yolov8m.pt
+data: /home/cuuva/experiment/vis6class_exp/vis6class.yaml
+epochs: 600
+time: null
+patience: 100
+batch: -1
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: vis6class_v8m
+name: 6class_final
+exist_ok: false
+pretrained: true
+optimizer: AdamW
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+compile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: true
+opset: null
+workspace: null
+nms: false
+lr0: 0.001
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: /home/cuuva/experiment/vis6class_exp/vis6class_v8m/6class_final

vis6class_exp/vis6class_v8m/6class_final/results.csv

@@ -0,0 +1,176 @@
+epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
+1,64.8035,1.44518,1.24871,0.96655,0.46273,0.30975,0.32292,0.19629,1.3705,1.01079,0.9411,0.0671222,0.000332099,0.000332099
+2,128.733,1.38532,1.05992,0.95003,0.45294,0.35537,0.35387,0.21002,1.35558,0.96973,0.93266,0.0341211,0.000664334,0.000664334
+3,192.989,1.41881,1.0677,0.956,0.5147,0.36667,0.38396,0.22674,1.35672,0.94898,0.93564,0.00111893,0.00099547,0.00099547
+4,257.349,1.36225,1.00021,0.94333,0.52509,0.3888,0.40765,0.24078,1.33336,0.92921,0.92681,0.00099505,0.00099505,0.00099505
+5,321.358,1.33899,0.95993,0.93652,0.53012,0.40704,0.43031,0.2576,1.30196,0.87481,0.91911,0.0009934,0.0009934,0.0009934
+6,385.205,1.31501,0.93258,0.93075,0.56913,0.41624,0.44554,0.27113,1.2617,0.85588,0.91127,0.00099175,0.00099175,0.00099175
+7,449.202,1.31006,0.91906,0.92719,0.59437,0.41488,0.45076,0.26983,1.28444,0.85635,0.91591,0.0009901,0.0009901,0.0009901
+8,513.371,1.30098,0.9078,0.92654,0.56587,0.43995,0.4606,0.27839,1.26495,0.84365,0.91303,0.00098845,0.00098845,0.00098845
+9,577.554,1.29198,0.89955,0.92354,0.60212,0.43087,0.47296,0.28981,1.23705,0.82191,0.90341,0.0009868,0.0009868,0.0009868
+10,641.466,1.28778,0.88534,0.92023,0.60386,0.42665,0.46924,0.28664,1.25422,0.83241,0.90805,0.00098515,0.00098515,0.00098515
+11,705.385,1.26663,0.86475,0.91755,0.62588,0.43605,0.48591,0.29631,1.22575,0.81091,0.90261,0.0009835,0.0009835,0.0009835
+12,769.296,1.26594,0.85902,0.91545,0.62306,0.43296,0.47924,0.2944,1.22424,0.80609,0.90126,0.00098185,0.00098185,0.00098185
+13,833.344,1.26118,0.85765,0.91652,0.61108,0.45652,0.49489,0.3044,1.21403,0.80677,0.89726,0.0009802,0.0009802,0.0009802
+14,897.373,1.25242,0.84303,0.91365,0.59442,0.4403,0.4741,0.28527,1.24185,0.81376,0.90497,0.00097855,0.00097855,0.00097855
+15,961.466,1.24375,0.83135,0.91025,0.59575,0.45481,0.48823,0.29908,1.22677,0.79404,0.90098,0.0009769,0.0009769,0.0009769
+16,1025.58,1.2372,0.83359,0.91098,0.59561,0.45908,0.48959,0.29972,1.22976,0.79903,0.90101,0.00097525,0.00097525,0.00097525
+17,1089.64,1.23689,0.82411,0.90922,0.61181,0.45519,0.49806,0.31014,1.21244,0.78897,0.89719,0.0009736,0.0009736,0.0009736
+18,1153.66,1.23348,0.81783,0.90767,0.60759,0.47299,0.50648,0.31392,1.19801,0.77305,0.89388,0.00097195,0.00097195,0.00097195
+19,1217.91,1.22053,0.80689,0.90553,0.63232,0.4683,0.50972,0.31608,1.19722,0.77999,0.89444,0.0009703,0.0009703,0.0009703
+20,1281.91,1.21907,0.7992,0.90579,0.61865,0.46849,0.50669,0.31537,1.19538,0.77569,0.89383,0.00096865,0.00096865,0.00096865
+21,1346,1.22905,0.8055,0.90632,0.61836,0.48083,0.51578,0.32058,1.18471,0.76918,0.88998,0.000967,0.000967,0.000967
+22,1410.13,1.21232,0.79165,0.90136,0.64282,0.46692,0.51349,0.32166,1.19824,0.77388,0.89219,0.00096535,0.00096535,0.00096535
+23,1474.04,1.20831,0.78677,0.90012,0.61244,0.47925,0.51026,0.32067,1.1791,0.7646,0.88943,0.0009637,0.0009637,0.0009637
+24,1538.2,1.20848,0.78101,0.89986,0.63258,0.47906,0.51905,0.32194,1.19256,0.77018,0.89139,0.00096205,0.00096205,0.00096205
+25,1602.18,1.19834,0.77934,0.89891,0.61344,0.48259,0.51653,0.32085,1.1845,0.76663,0.89126,0.0009604,0.0009604,0.0009604
+26,1666.24,1.20063,0.77599,0.89973,0.62179,0.47035,0.50913,0.32007,1.17346,0.76121,0.8888,0.00095875,0.00095875,0.00095875
+27,1730.08,1.19376,0.76545,0.89727,0.63575,0.47863,0.52479,0.32763,1.17068,0.75212,0.88685,0.0009571,0.0009571,0.0009571
+28,1794.03,1.18805,0.76469,0.89782,0.63668,0.47719,0.52512,0.3255,1.18985,0.76704,0.89239,0.00095545,0.00095545,0.00095545
+29,1857.95,1.18989,0.765,0.89541,0.62915,0.4853,0.52832,0.33179,1.16844,0.74669,0.88637,0.0009538,0.0009538,0.0009538
+30,1921.79,1.18171,0.75651,0.8955,0.63057,0.47255,0.51411,0.32262,1.16901,0.75514,0.88692,0.00095215,0.00095215,0.00095215
+31,1985.71,1.18705,0.75535,0.89317,0.65119,0.47569,0.52727,0.32381,1.17397,0.74966,0.88879,0.0009505,0.0009505,0.0009505
+32,2049.54,1.18147,0.74567,0.89288,0.62949,0.48971,0.52612,0.33159,1.16884,0.74622,0.88706,0.00094885,0.00094885,0.00094885
+33,2113.65,1.16978,0.73852,0.89109,0.64428,0.47537,0.52524,0.32652,1.16018,0.7442,0.88446,0.0009472,0.0009472,0.0009472
+34,2177.42,1.16995,0.73718,0.89148,0.63579,0.48866,0.53245,0.33599,1.15473,0.73998,0.88402,0.00094555,0.00094555,0.00094555
+35,2241.33,1.17518,0.73971,0.89094,0.65465,0.48555,0.53581,0.33659,1.16395,0.74569,0.88555,0.0009439,0.0009439,0.0009439
+36,2305.47,1.17048,0.73297,0.8924,0.65071,0.48114,0.53187,0.33396,1.16779,0.74155,0.88597,0.00094225,0.00094225,0.00094225
+37,2369.59,1.17018,0.73188,0.89036,0.64599,0.4981,0.53902,0.33702,1.15918,0.73711,0.88496,0.0009406,0.0009406,0.0009406
+38,2433.43,1.16699,0.72944,0.89132,0.64679,0.48783,0.53388,0.33523,1.1555,0.73802,0.88384,0.00093895,0.00093895,0.00093895
+39,2497.58,1.16514,0.72808,0.88999,0.63368,0.49484,0.53736,0.33742,1.16042,0.7363,0.88373,0.0009373,0.0009373,0.0009373
+40,2561.57,1.16183,0.7236,0.88981,0.6531,0.48973,0.53759,0.33943,1.15121,0.72778,0.88335,0.00093565,0.00093565,0.00093565
+41,2625.73,1.1525,0.71356,0.88643,0.64971,0.49286,0.541,0.33899,1.15809,0.73146,0.88337,0.000934,0.000934,0.000934
+42,2689.81,1.16028,0.71917,0.88767,0.67032,0.48375,0.5427,0.34212,1.15283,0.72921,0.88257,0.00093235,0.00093235,0.00093235
+43,2753.73,1.15168,0.71054,0.8874,0.64121,0.48447,0.53189,0.33567,1.14694,0.73498,0.88224,0.0009307,0.0009307,0.0009307
+44,2817.52,1.15014,0.70671,0.88659,0.67361,0.4827,0.53749,0.34003,1.1481,0.7262,0.88326,0.00092905,0.00092905,0.00092905
+45,2881.37,1.14727,0.70715,0.88606,0.66705,0.49305,0.5469,0.34298,1.15,0.72862,0.88311,0.0009274,0.0009274,0.0009274
+46,2945.31,1.15125,0.70263,0.8862,0.65777,0.49505,0.54361,0.34189,1.14581,0.72585,0.88264,0.00092575,0.00092575,0.00092575
+47,3009.27,1.14535,0.69739,0.88502,0.65319,0.49376,0.5386,0.33972,1.14944,0.7301,0.88347,0.0009241,0.0009241,0.0009241
+48,3073.15,1.14672,0.69879,0.88624,0.65801,0.49213,0.54074,0.34253,1.14168,0.7217,0.8813,0.00092245,0.00092245,0.00092245
+49,3137.08,1.13833,0.69601,0.88406,0.6831,0.48304,0.54416,0.34159,1.1445,0.72569,0.88159,0.0009208,0.0009208,0.0009208
+50,3201.04,1.13329,0.68679,0.88318,0.67247,0.49799,0.54747,0.34572,1.14426,0.72013,0.88211,0.00091915,0.00091915,0.00091915
+51,3264.99,1.13471,0.68751,0.8815,0.64192,0.50293,0.54212,0.3426,1.14077,0.72725,0.88076,0.0009175,0.0009175,0.0009175
+52,3328.91,1.13095,0.68484,0.88112,0.64944,0.50383,0.54335,0.34207,1.14459,0.72942,0.88187,0.00091585,0.00091585,0.00091585
+53,3392.92,1.13338,0.68141,0.88166,0.66191,0.49664,0.5454,0.34356,1.1425,0.72184,0.88272,0.0009142,0.0009142,0.0009142
+54,3457.21,1.12874,0.67776,0.88055,0.6693,0.50191,0.54906,0.34847,1.1399,0.72244,0.881,0.00091255,0.00091255,0.00091255
+55,3521.2,1.12667,0.67808,0.88172,0.66195,0.50304,0.54449,0.34522,1.14364,0.7225,0.88014,0.0009109,0.0009109,0.0009109
+56,3585.24,1.12688,0.67354,0.88167,0.66481,0.49133,0.54145,0.34078,1.14103,0.71977,0.88097,0.00090925,0.00090925,0.00090925
+57,3649.13,1.12425,0.66795,0.8794,0.67781,0.48963,0.54656,0.34558,1.13977,0.72294,0.87996,0.0009076,0.0009076,0.0009076
+58,3713.36,1.11582,0.66389,0.87772,0.66708,0.50037,0.54724,0.34554,1.14188,0.72441,0.88116,0.00090595,0.00090595,0.00090595
+59,3777.38,1.12489,0.67057,0.88185,0.67666,0.49768,0.54776,0.3485,1.13654,0.72016,0.87997,0.0009043,0.0009043,0.0009043
+60,3841.56,1.11509,0.6632,0.87877,0.65721,0.50707,0.54991,0.34861,1.13682,0.72234,0.87989,0.00090265,0.00090265,0.00090265
+61,3905.67,1.11431,0.6636,0.87926,0.66807,0.5013,0.5489,0.34585,1.13701,0.72071,0.87988,0.000901,0.000901,0.000901
+62,3969.6,1.11513,0.65643,0.87666,0.65831,0.50355,0.54546,0.34632,1.13513,0.71827,0.87947,0.00089935,0.00089935,0.00089935
+63,4033.5,1.12089,0.66283,0.87836,0.65734,0.49676,0.54185,0.344,1.13705,0.72326,0.87983,0.0008977,0.0008977,0.0008977
+64,4097.4,1.11201,0.65618,0.87594,0.66989,0.49881,0.54563,0.34639,1.13791,0.72075,0.88058,0.00089605,0.00089605,0.00089605
+65,4161.29,1.11211,0.65779,0.87727,0.66857,0.50234,0.54927,0.34727,1.13659,0.71555,0.88045,0.0008944,0.0008944,0.0008944
+66,4225.47,1.11522,0.65243,0.87697,0.66791,0.50309,0.55517,0.35026,1.13522,0.71725,0.87946,0.00089275,0.00089275,0.00089275
+67,4289.54,1.10976,0.65186,0.8775,0.66748,0.50032,0.54999,0.34741,1.1305,0.71752,0.87916,0.0008911,0.0008911,0.0008911
+68,4353.69,1.10584,0.64679,0.87566,0.66842,0.5073,0.55186,0.34668,1.13592,0.71847,0.87917,0.00088945,0.00088945,0.00088945
+69,4417.64,1.09867,0.64043,0.87553,0.67337,0.50941,0.55703,0.35388,1.12921,0.71507,0.87929,0.0008878,0.0008878,0.0008878
+70,4481.6,1.10444,0.6455,0.87573,0.66762,0.50716,0.55429,0.35244,1.13469,0.71804,0.88071,0.00088615,0.00088615,0.00088615
+71,4545.55,1.09745,0.63946,0.87383,0.68035,0.50724,0.55708,0.35418,1.12982,0.71907,0.87833,0.0008845,0.0008845,0.0008845
+72,4609.77,1.10444,0.645,0.87366,0.66764,0.50861,0.55693,0.35152,1.13669,0.71818,0.87958,0.00088285,0.00088285,0.00088285
+73,4673.69,1.0917,0.6343,0.87172,0.67272,0.50578,0.55328,0.34915,1.13583,0.72413,0.87934,0.0008812,0.0008812,0.0008812
+74,4737.63,1.09022,0.62993,0.87131,0.67156,0.50179,0.5534,0.35196,1.13051,0.71811,0.87903,0.00087955,0.00087955,0.00087955
+75,4801.46,1.08989,0.62971,0.87234,0.65897,0.51301,0.55478,0.35424,1.13245,0.71703,0.87879,0.0008779,0.0008779,0.0008779
+76,4865.63,1.09852,0.63366,0.87418,0.655,0.51138,0.55247,0.35138,1.13346,0.72068,0.87948,0.00087625,0.00087625,0.00087625
+77,4929.52,1.08843,0.62825,0.87022,0.67329,0.50409,0.55324,0.35166,1.12838,0.72232,0.87899,0.0008746,0.0008746,0.0008746
+78,4993.39,1.08913,0.62332,0.87072,0.68063,0.50358,0.55446,0.35042,1.13237,0.72265,0.87992,0.00087295,0.00087295,0.00087295
+79,5057.52,1.0887,0.62448,0.8701,0.68301,0.5032,0.55435,0.35013,1.13164,0.71981,0.88062,0.0008713,0.0008713,0.0008713
+80,5121.71,1.08269,0.61771,0.86959,0.67308,0.50434,0.55055,0.34776,1.13235,0.72501,0.8799,0.00086965,0.00086965,0.00086965
+81,5185.64,1.07984,0.61672,0.8701,0.67472,0.51399,0.55649,0.35101,1.13306,0.72164,0.88022,0.000868,0.000868,0.000868
+82,5249.68,1.07391,0.61233,0.86904,0.67007,0.5117,0.55377,0.34889,1.13213,0.71981,0.8799,0.00086635,0.00086635,0.00086635
+83,5313.64,1.0915,0.62505,0.87071,0.67053,0.51382,0.5542,0.3518,1.13241,0.71669,0.88015,0.0008647,0.0008647,0.0008647
+84,5377.76,1.08274,0.61858,0.86924,0.67007,0.51492,0.554,0.35063,1.12959,0.72378,0.87993,0.00086305,0.00086305,0.00086305
+85,5441.59,1.0703,0.60979,0.86879,0.67028,0.50742,0.55333,0.34934,1.13234,0.72197,0.87962,0.0008614,0.0008614,0.0008614
+86,5505.63,1.077,0.61056,0.86852,0.65932,0.51801,0.55319,0.34892,1.1292,0.7205,0.87976,0.00085975,0.00085975,0.00085975
+87,5569.71,1.07485,0.61264,0.86836,0.66481,0.51436,0.55293,0.35019,1.1314,0.71981,0.87986,0.0008581,0.0008581,0.0008581
+88,5633.51,1.06894,0.60671,0.86749,0.67424,0.50364,0.55369,0.35028,1.12878,0.71955,0.87965,0.00085645,0.00085645,0.00085645
+89,5697.43,1.07399,0.6084,0.86845,0.67186,0.50223,0.55047,0.34952,1.13167,0.72561,0.8798,0.0008548,0.0008548,0.0008548
+90,5761.53,1.06952,0.60621,0.8688,0.65714,0.51069,0.54978,0.34836,1.13385,0.72643,0.88086,0.00085315,0.00085315,0.00085315
+91,5825.73,1.0756,0.60874,0.86808,0.67593,0.50725,0.55125,0.34984,1.13306,0.72452,0.88113,0.0008515,0.0008515,0.0008515
+92,5889.74,1.07183,0.6045,0.86655,0.67137,0.50689,0.55205,0.34957,1.13212,0.7247,0.88026,0.00084985,0.00084985,0.00084985
+93,5953.77,1.06909,0.60325,0.86693,0.6606,0.50999,0.5511,0.34813,1.1307,0.72477,0.88009,0.0008482,0.0008482,0.0008482
+94,6017.98,1.06868,0.59819,0.8659,0.68322,0.49889,0.55086,0.34968,1.13179,0.72591,0.88046,0.00084655,0.00084655,0.00084655
+95,6082.01,1.05942,0.59723,0.8664,0.6852,0.50147,0.55346,0.35114,1.13373,0.72241,0.88192,0.0008449,0.0008449,0.0008449
+96,6145.9,1.05893,0.59289,0.86423,0.66682,0.50966,0.55433,0.35088,1.13276,0.72234,0.88136,0.00084325,0.00084325,0.00084325
+97,6210.04,1.06301,0.59375,0.86454,0.66694,0.50716,0.55264,0.35205,1.13275,0.72377,0.88118,0.0008416,0.0008416,0.0008416
+98,6273.91,1.06074,0.59305,0.86506,0.66494,0.50852,0.55146,0.34935,1.13161,0.72461,0.88084,0.00083995,0.00083995,0.00083995
+99,6337.73,1.06084,0.59227,0.86463,0.66634,0.51215,0.55356,0.35078,1.13027,0.72471,0.88097,0.0008383,0.0008383,0.0008383
+100,6401.55,1.05704,0.59204,0.86543,0.6699,0.51056,0.55416,0.35218,1.13266,0.72449,0.88103,0.00083665,0.00083665,0.00083665
+101,6465.41,1.05845,0.59215,0.86499,0.67652,0.50625,0.55434,0.35261,1.13203,0.72237,0.88132,0.000835,0.000835,0.000835
+102,6529.24,1.05855,0.59032,0.86438,0.68147,0.50831,0.5554,0.35309,1.13348,0.72366,0.88215,0.00083335,0.00083335,0.00083335
+103,6593.34,1.04906,0.58376,0.86221,0.67315,0.51159,0.55654,0.35352,1.13284,0.72488,0.88155,0.0008317,0.0008317,0.0008317
+104,6657.43,1.05537,0.58667,0.8631,0.6874,0.50953,0.55661,0.35209,1.13384,0.72472,0.88206,0.00083005,0.00083005,0.00083005
+105,6721.32,1.05584,0.58685,0.86302,0.68912,0.50328,0.55256,0.35034,1.13486,0.72571,0.88185,0.0008284,0.0008284,0.0008284
+106,6785.3,1.05025,0.58386,0.86156,0.67477,0.51341,0.5544,0.35084,1.13437,0.72376,0.88185,0.00082675,0.00082675,0.00082675
+107,6849.13,1.04294,0.57856,0.86364,0.67935,0.51248,0.55402,0.35082,1.13324,0.72233,0.88183,0.0008251,0.0008251,0.0008251
+108,6912.99,1.04676,0.57953,0.86253,0.67312,0.51609,0.55647,0.35225,1.13229,0.72598,0.88192,0.00082345,0.00082345,0.00082345
+109,6977.08,1.04805,0.58048,0.86251,0.64971,0.52309,0.55442,0.35182,1.13208,0.72577,0.88147,0.0008218,0.0008218,0.0008218
+110,7040.97,1.04438,0.5779,0.86216,0.66714,0.51648,0.55406,0.3513,1.13224,0.72763,0.88204,0.00082015,0.00082015,0.00082015
+111,7105.05,1.04103,0.572,0.86076,0.68105,0.51288,0.55611,0.35236,1.13281,0.7258,0.88215,0.0008185,0.0008185,0.0008185
+112,7168.85,1.04171,0.57668,0.86113,0.66468,0.52007,0.55723,0.3535,1.13323,0.72519,0.88274,0.00081685,0.00081685,0.00081685
+113,7232.74,1.03923,0.57297,0.86001,0.66402,0.51804,0.55718,0.35329,1.13378,0.72517,0.88255,0.0008152,0.0008152,0.0008152
+114,7296.86,1.03079,0.5682,0.8588,0.67095,0.51772,0.55727,0.35329,1.13437,0.72443,0.88221,0.00081355,0.00081355,0.00081355
+115,7360.97,1.03641,0.56569,0.85791,0.67918,0.51061,0.55604,0.35278,1.13426,0.72551,0.88249,0.0008119,0.0008119,0.0008119
+116,7424.79,1.03328,0.56741,0.86111,0.6711,0.51433,0.55457,0.35196,1.13681,0.72667,0.88327,0.00081025,0.00081025,0.00081025
+117,7488.74,1.03303,0.56748,0.86006,0.67779,0.51406,0.55545,0.35161,1.13704,0.72713,0.88365,0.0008086,0.0008086,0.0008086
+118,7552.81,1.03389,0.56918,0.85857,0.66465,0.52047,0.55381,0.34991,1.13708,0.7282,0.88388,0.00080695,0.00080695,0.00080695
+119,7616.54,1.03357,0.56887,0.85959,0.66975,0.51673,0.5536,0.35017,1.13596,0.72758,0.88399,0.0008053,0.0008053,0.0008053
+120,7680.41,1.02314,0.55949,0.85958,0.67207,0.51184,0.55282,0.34957,1.1357,0.72921,0.88408,0.00080365,0.00080365,0.00080365
+121,7744.51,1.03528,0.56551,0.85896,0.66501,0.51603,0.5527,0.34874,1.13506,0.72942,0.88371,0.000802,0.000802,0.000802
+122,7808.32,1.02428,0.56044,0.8584,0.66364,0.51467,0.55249,0.34852,1.13462,0.7299,0.8834,0.00080035,0.00080035,0.00080035
+123,7872.32,1.02822,0.56344,0.85863,0.65986,0.51624,0.553,0.34945,1.13644,0.73018,0.88363,0.0007987,0.0007987,0.0007987
+124,7936.39,1.03015,0.56336,0.85678,0.65655,0.51864,0.55417,0.35048,1.13726,0.73125,0.88362,0.00079705,0.00079705,0.00079705
+125,8000.48,1.02651,0.56362,0.8583,0.65915,0.51812,0.55379,0.35069,1.13676,0.73003,0.88364,0.0007954,0.0007954,0.0007954
+126,8064.31,1.0297,0.56073,0.85847,0.66272,0.51678,0.55289,0.35062,1.13578,0.72939,0.88339,0.00079375,0.00079375,0.00079375
+127,8128.28,1.02396,0.55684,0.85469,0.661,0.51863,0.55149,0.34905,1.13634,0.73048,0.8837,0.0007921,0.0007921,0.0007921
+128,8192.06,1.01717,0.55376,0.85612,0.66481,0.51631,0.55126,0.34887,1.13553,0.73112,0.88385,0.00079045,0.00079045,0.00079045
+129,8256.38,1.02283,0.55599,0.85613,0.67058,0.51584,0.55172,0.34792,1.13536,0.73156,0.8839,0.0007888,0.0007888,0.0007888
+130,8320.32,1.0258,0.55782,0.85678,0.66638,0.51726,0.55244,0.34785,1.13523,0.73115,0.88401,0.00078715,0.00078715,0.00078715
+131,8384.46,1.01587,0.55501,0.85619,0.66601,0.51425,0.5522,0.3479,1.13498,0.73134,0.884,0.0007855,0.0007855,0.0007855
+132,8448.37,1.01501,0.55109,0.85626,0.66878,0.51446,0.55208,0.34836,1.13563,0.73171,0.88418,0.00078385,0.00078385,0.00078385
+133,8512.26,1.01238,0.54966,0.8545,0.67126,0.51412,0.55145,0.34887,1.13602,0.73269,0.88405,0.0007822,0.0007822,0.0007822
+134,8576.46,1.01704,0.55273,0.85584,0.68169,0.50635,0.55135,0.34823,1.13514,0.73211,0.88399,0.00078055,0.00078055,0.00078055
+135,8640.32,1.01448,0.55054,0.85395,0.67828,0.50893,0.55219,0.34882,1.1356,0.73239,0.88407,0.0007789,0.0007789,0.0007789
+136,8704.41,1.01297,0.54947,0.85442,0.68237,0.50502,0.55136,0.34922,1.13583,0.73254,0.8839,0.00077725,0.00077725,0.00077725
+137,8768.43,1.01278,0.54742,0.85463,0.67332,0.5096,0.55168,0.34973,1.13671,0.73254,0.88407,0.0007756,0.0007756,0.0007756
+138,8832.29,1.01271,0.54791,0.85515,0.6777,0.50789,0.55138,0.34941,1.13641,0.73376,0.88409,0.00077395,0.00077395,0.00077395
+139,8896.14,1.00708,0.54649,0.85457,0.68264,0.5068,0.55109,0.34879,1.13625,0.73337,0.88417,0.0007723,0.0007723,0.0007723
+140,8959.92,1.00589,0.54721,0.85353,0.68586,0.5059,0.55099,0.34856,1.13684,0.7338,0.88433,0.00077065,0.00077065,0.00077065
+141,9023.68,1.01197,0.54497,0.85557,0.68826,0.50547,0.5517,0.34833,1.13624,0.73378,0.88418,0.000769,0.000769,0.000769
+142,9087.77,1.00994,0.5461,0.85498,0.6827,0.50763,0.55145,0.34852,1.136,0.73374,0.88404,0.00076735,0.00076735,0.00076735
+143,9151.79,1.00489,0.54407,0.85265,0.6722,0.51226,0.55141,0.34962,1.13494,0.73426,0.88372,0.0007657,0.0007657,0.0007657
+144,9215.86,1.00291,0.54088,0.85307,0.66429,0.51626,0.55203,0.34981,1.13518,0.73452,0.88378,0.00076405,0.00076405,0.00076405
+145,9279.89,1.0037,0.54351,0.85326,0.66512,0.51543,0.55162,0.34945,1.13457,0.73382,0.88359,0.0007624,0.0007624,0.0007624
+146,9343.84,1.00555,0.54271,0.85324,0.66167,0.51907,0.55163,0.34959,1.13497,0.73373,0.88385,0.00076075,0.00076075,0.00076075
+147,9407.66,0.99876,0.5389,0.85363,0.65881,0.5197,0.55177,0.3492,1.13441,0.7335,0.88366,0.0007591,0.0007591,0.0007591
+148,9471.57,0.99579,0.53835,0.85242,0.66106,0.51696,0.55085,0.34901,1.13446,0.73316,0.88357,0.00075745,0.00075745,0.00075745
+149,9535.77,1.00651,0.54226,0.85207,0.66219,0.51447,0.55106,0.34892,1.13452,0.73249,0.88349,0.0007558,0.0007558,0.0007558
+150,9599.69,1.00348,0.53746,0.85181,0.66458,0.51443,0.55139,0.34975,1.13458,0.73227,0.88355,0.00075415,0.00075415,0.00075415
+151,9663.78,0.99815,0.53816,0.85026,0.66469,0.5146,0.55146,0.34974,1.13496,0.7321,0.88361,0.0007525,0.0007525,0.0007525
+152,9727.62,0.99518,0.53571,0.85231,0.66481,0.51608,0.55179,0.3496,1.13502,0.73167,0.88374,0.00075085,0.00075085,0.00075085
+153,9791.55,0.99609,0.53557,0.85246,0.66681,0.51391,0.55148,0.34929,1.13497,0.73164,0.88389,0.0007492,0.0007492,0.0007492
+154,9855.69,0.98625,0.52876,0.84867,0.67153,0.5128,0.5508,0.34908,1.13498,0.73194,0.88399,0.00074755,0.00074755,0.00074755
+155,9919.59,0.99132,0.5326,0.85064,0.67047,0.5128,0.55033,0.34838,1.13494,0.73264,0.88404,0.0007459,0.0007459,0.0007459
+156,9983.69,0.99157,0.53136,0.85102,0.6721,0.51393,0.55079,0.34831,1.13473,0.73255,0.88403,0.00074425,0.00074425,0.00074425
+157,10047.8,0.99016,0.5309,0.8512,0.67463,0.51134,0.55099,0.34806,1.13433,0.73258,0.88378,0.0007426,0.0007426,0.0007426
+158,10111.7,0.98982,0.53259,0.85117,0.67612,0.50967,0.5509,0.34767,1.13427,0.73305,0.88375,0.00074095,0.00074095,0.00074095
+159,10175.6,0.98865,0.53309,0.84996,0.67514,0.50914,0.55105,0.34823,1.1343,0.73355,0.88382,0.0007393,0.0007393,0.0007393
+160,10239.4,0.99202,0.52971,0.85173,0.67624,0.50778,0.55086,0.34831,1.13407,0.73311,0.88381,0.00073765,0.00073765,0.00073765
+161,10303.2,0.98676,0.52927,0.85012,0.67593,0.50735,0.55064,0.34804,1.13416,0.73365,0.88386,0.000736,0.000736,0.000736
+162,10367,0.98663,0.52832,0.84805,0.675,0.509,0.55026,0.34768,1.13431,0.73386,0.88398,0.00073435,0.00073435,0.00073435
+163,10431.1,0.98261,0.52547,0.84916,0.67632,0.50844,0.55082,0.34759,1.13458,0.73427,0.88413,0.0007327,0.0007327,0.0007327
+164,10495.1,0.98621,0.52532,0.84968,0.675,0.5103,0.54973,0.34755,1.1346,0.73448,0.8841,0.00073105,0.00073105,0.00073105
+165,10559.2,0.98422,0.52592,0.84989,0.67198,0.51332,0.54915,0.34749,1.13463,0.73555,0.88414,0.0007294,0.0007294,0.0007294
+166,10623.2,0.98072,0.52351,0.84915,0.67387,0.51222,0.54926,0.34783,1.13492,0.73591,0.88419,0.00072775,0.00072775,0.00072775
+167,10687.3,0.97795,0.5218,0.84846,0.6759,0.51134,0.54982,0.34829,1.13551,0.73583,0.88417,0.0007261,0.0007261,0.0007261
+168,10751.3,0.98896,0.52968,0.84838,0.6749,0.51194,0.55036,0.34836,1.13566,0.73555,0.88402,0.00072445,0.00072445,0.00072445
+169,10815.3,0.97516,0.51849,0.84661,0.67322,0.51221,0.55035,0.34862,1.13581,0.73567,0.88404,0.0007228,0.0007228,0.0007228
+170,10879.1,0.98088,0.5221,0.8475,0.67445,0.51068,0.55027,0.34872,1.13608,0.73612,0.88414,0.00072115,0.00072115,0.00072115
+171,10943.2,0.98014,0.52431,0.84878,0.67273,0.5111,0.55064,0.3487,1.13588,0.7364,0.88425,0.0007195,0.0007195,0.0007195
+172,11007.4,0.97471,0.52028,0.84837,0.67331,0.51107,0.55102,0.3489,1.13588,0.73633,0.88425,0.00071785,0.00071785,0.00071785
+173,11071.2,0.9762,0.5198,0.84799,0.67464,0.51164,0.55129,0.34919,1.13599,0.73674,0.88439,0.0007162,0.0007162,0.0007162
+174,11135.3,0.97357,0.5202,0.84948,0.67465,0.51303,0.55157,0.34897,1.13609,0.73653,0.88431,0.00071455,0.00071455,0.00071455
+175,11199.1,0.97646,0.51946,0.84684,0.67474,0.51296,0.55146,0.34871,1.13585,0.73623,0.88431,0.0007129,0.0007129,0.0007129