From 35c9f9cb5d19eeb9b8781a3f2cbb61edc367fd2e Mon Sep 17 00:00:00 2001
From: songhyeonsu <hunsoo0823@naver.com>
Date: Thu, 7 May 2026 14:25:34 +0900
Subject: [PATCH] Initial scaffold for kr_lp_pgnet

- README outlines local-server split workflow
- setup_server.sh installs paddlepaddle-gpu, clones PaddleOCR, fetches PGNet step1 pretrain
- empty configs/dict/data_gen/tools dirs for next steps

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---
 .gitignore              | 34 ++++++++++++++++++++++++++
 README.md               | 54 ++++++++++++++++++++++++++++++++++++++++-
 configs/.gitkeep        |  0
 data_gen/.gitkeep       |  0
 dict/.gitkeep           |  0
 scripts/setup_server.sh | 39 +++++++++++++++++++++++++++++
 tools/.gitkeep          |  0
 7 files changed, 126 insertions(+), 1 deletion(-)
 create mode 100644 .gitignore
 create mode 100644 configs/.gitkeep
 create mode 100644 data_gen/.gitkeep
 create mode 100644 dict/.gitkeep
 create mode 100755 scripts/setup_server.sh
 create mode 100644 tools/.gitkeep

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..e0a65c7
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,34 @@
+# 학습 산출물
+output/
+inference/
+pretrain_models/
+*.pdparams
+*.pdopt
+*.states
+*.tar
+*.pdmodel
+*.pdiparams
+*.pdiparams.info
+
+# 데이터셋 (서버에서 생성, 로컬엔 샘플만)
+train_data/
+data_gen/plate_templates/*.png
+data_gen/plate_templates/*.jpg
+!data_gen/plate_templates/.gitkeep
+
+# 파이썬
+__pycache__/
+*.pyc
+*.pyo
+.venv/
+venv/
+.ipynb_checkpoints/
+
+# OS / IDE
+.DS_Store
+.vscode/
+.idea/
+
+# 로그
+*.log
+log/
diff --git a/README.md b/README.md
index 1e38c85..0f788d0 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,54 @@
-# PGNET
+# kr_lp_pgnet
 
+PaddleOCR PGNet 기반 한국 번호판(LP) end-to-end 검출 + OCR 학습 프로젝트.
+
+대상 번호판: 승용(흰), 영업용(노란), 전기차(파란 8자리), 화물·특수.
+
+## 디렉토리 구조
+
+```
+kr_lp_pgnet/
+├── configs/        # PGNet 학습 config (.yml)
+├── dict/           # 문자 사전 (kr_lp_dict.txt)
+├── data_gen/       # 합성 LP 이미지 생성기
+├── scripts/        # 서버 셋업·학습 실행 셸 스크립트
+└── tools/          # 라벨 검증·시각화 등 보조 스크립트
+```
+
+## 작업 분업
+
+- **로컬 (Mac)**: config·dict·생성기·run script 작성 및 디버깅
+- **원격 GPU 서버 (NVIDIA + CUDA)**: 합성 데이터 생성, 학습 실행
+- 동기화: 이 repo는 git push/pull, 데이터·체크포인트는 git에 올리지 않음
+
+## 서버 측 실행 순서
+
+```bash
+# 1. 최초 1회: 환경 셋업 (Paddle 설치 + PaddleOCR clone + pretrain weight 다운로드)
+bash scripts/setup_server.sh
+
+# 2. 합성 데이터 생성 (수십만장)
+python data_gen/generate_synthetic.py --out_dir ../train_data/kr_lp_synth --num 200000
+
+# 3. Step1: 합성 데이터로 pretrain
+bash scripts/run_step1.sh
+
+# 4. Step2: 실제 LP 데이터로 fine-tune
+bash scripts/run_step2.sh
+
+# 5. 추론 모델로 export
+bash scripts/export_inference.sh
+```
+
+## 디렉토리 가정
+
+서버에서는 다음 레이아웃을 가정:
+
+```
+~/workspace/
+├── PaddleOCR/              # git clone PaddlePaddle/PaddleOCR
+├── kr_lp_pgnet/            # 이 repo
+└── train_data/
+    ├── kr_lp_synth/        # 합성 데이터 (생성기 출력)
+    └── kr_lp_real/         # 실제 촬영 LP 데이터
+```
diff --git a/configs/.gitkeep b/configs/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/data_gen/.gitkeep b/data_gen/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/dict/.gitkeep b/dict/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/scripts/setup_server.sh b/scripts/setup_server.sh
new file mode 100755
index 0000000..d31924d
--- /dev/null
+++ b/scripts/setup_server.sh
@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+# 외부 GPU 서버 최초 1회 셋업
+# 가정: NVIDIA GPU + CUDA 11.8 (다른 CUDA면 paddle wheel URL 수정)
+# 실행 위치: ~/workspace/kr_lp_pgnet/
+
+set -euo pipefail
+
+WORKSPACE="${WORKSPACE:-$HOME/workspace}"
+PADDLEOCR_DIR="$WORKSPACE/PaddleOCR"
+PRETRAIN_DIR="$PADDLEOCR_DIR/pretrain_models"
+
+echo "[1/4] PaddlePaddle GPU 설치 (CUDA 11.8 기준)"
+python3 -m pip install --upgrade pip
+python3 -m pip install paddlepaddle-gpu==2.6.1.post118 \
+    -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html
+
+echo "[2/4] PaddleOCR clone"
+if [ ! -d "$PADDLEOCR_DIR" ]; then
+    git clone --depth 1 -b release/2.7 https://github.com/PaddlePaddle/PaddleOCR.git "$PADDLEOCR_DIR"
+fi
+cd "$PADDLEOCR_DIR"
+python3 -m pip install -r requirements.txt
+
+echo "[3/4] PGNet Step1 pretrain weight 다운로드"
+mkdir -p "$PRETRAIN_DIR"
+cd "$PRETRAIN_DIR"
+if [ ! -d "train_step1" ]; then
+    wget -q https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/train_step1.tar
+    tar xf train_step1.tar
+    rm train_step1.tar
+fi
+
+echo "[4/4] GPU/Paddle 동작 확인"
+python3 -c "import paddle; print('paddle:', paddle.__version__); print('CUDA available:', paddle.is_compiled_with_cuda()); print('GPU count:', paddle.device.cuda.device_count())"
+
+echo
+echo "셋업 완료. 다음 단계:"
+echo "  python data_gen/generate_synthetic.py ..."
+echo "  bash scripts/run_step1.sh"
diff --git a/tools/.gitkeep b/tools/.gitkeep
new file mode 100644
index 0000000..e69de29