Detection_Experiment/fashion_yolo/aihub_dataset_eda.ipynb

{
 "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
}