MiniGPT-4/create_dataset.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from pathlib import Path\n",
    "import glob\n",
    "import cv2\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "BASE_DIR = Path(\"./MVTEC\")\n",
    "NEW_DIR = Path(\"./MVTEC_det\")\n",
    "NEW_DIR.mkdir(exist_ok=True)\n",
    "\n",
    "class_names = [\"bottle\", \"cable\", \"capsule\", \"carpet\", \"grid\", \"hazelnut\", \"leather\", \"metal_nut\", \"pill\", \"screw\", \"tile\", \"toothbrush\", \"transistor\", \"wood\", \"zipper\"]\n",
    "base_split = [\"train\", \"test\"]\n",
    "base_cate = [\"good\", \"defect\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def normalize_bbox(bbox, width, height):\n",
    "    \"\"\"\n",
    "    Normalize bounding box to the range [0, 100].\n",
    "    \"\"\"\n",
    "    return [\n",
    "        int((bbox[0] / width) * 100),  # x_min\n",
    "        int((bbox[1] / height) * 100),  # y_min\n",
    "        int((bbox[2] / width) * 100),  # x_max\n",
    "        int((bbox[3] / height) * 100),  # y_max\n",
    "    ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processing bottle\n",
      "Processing cable\n",
      "Processing capsule\n",
      "Processing carpet\n",
      "Processing grid\n",
      "Processing hazelnut\n",
      "Processing leather\n",
      "Processing metal_nut\n",
      "Processing pill\n",
      "Processing screw\n",
      "Processing tile\n",
      "Processing toothbrush\n",
      "Processing transistor\n",
      "Processing wood\n",
      "Processing zipper\n"
     ]
    }
   ],
   "source": [
    "mvtech_ad_data_for_regression = []\n",
    "\n",
    "for class_name in class_names:\n",
    "    print(f\"Processing {class_name}\")\n",
    "    class_dir = Path(BASE_DIR) / class_name\n",
    "    new_class_dir = NEW_DIR / class_name\n",
    "    new_class_dir.mkdir(exist_ok=True)\n",
    "    \n",
    "    for split in base_split:\n",
    "        if split == \"train\":\n",
    "            cmd = f\"cp -r {class_dir / split}/good {new_class_dir}/\"\n",
    "            os.system(cmd)\n",
    "\n",
    "            image_paths = glob.glob(f\"{new_class_dir}/good/*.png\")\n",
    "            for image_path in image_paths:\n",
    "                img = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)\n",
    "                # bbox is the image size\n",
    "                bbox = [0, 0, img.shape[1], img.shape[0]]\n",
    "                mvtech_ad_data_for_regression.append({\n",
    "                    \"image_path\": image_path,\n",
    "                    \"bbox\": bbox,\n",
    "                    \"class\": class_name,\n",
    "                    \"is_broken\": False,\n",
    "                    \"height\": img.shape[0],\n",
    "                    \"width\": img.shape[1]\n",
    "                })\n",
    "\n",
    "        else:\n",
    "            new_broken_dir = new_class_dir / \"broken\"\n",
    "            new_broken_dir.mkdir(exist_ok=True)\n",
    "\n",
    "            last_good_idx = int(sorted(glob.glob(f'{class_dir}/train/good/*.png'))[-1].split('/')[-1].split('.')[0])\n",
    "            good_images = sorted(glob.glob(f\"{class_dir / split}/good/*.png\"))\n",
    "            for i, good_image in enumerate(good_images):\n",
    "                new_name = good_image.split(\"/\")[:-1] + [f\"{last_good_idx+i+1:03d}.png\"]\n",
    "                new_name.remove(\"test\")\n",
    "                new_name = \"/\".join(new_name)\n",
    "                new_name = new_name.replace(\"MVTEC\", \"MVTEC_det\")\n",
    "                cmd = f\"cp {good_image} {new_name}\"\n",
    "                os.system(cmd)\n",
    "\n",
    "                img = cv2.imread(new_name, cv2.IMREAD_GRAYSCALE)\n",
    "                bbox = [0, 0, img.shape[1], img.shape[0]]\n",
    "                mvtech_ad_data_for_regression.append({\n",
    "                    \"image_path\": new_name,\n",
    "                    \"bbox\": bbox,\n",
    "                    \"class\": class_name,\n",
    "                    \"is_broken\": False,\n",
    "                    \"height\": 256,\n",
    "                    \"width\": 256\n",
    "                })\n",
    "\n",
    "            broken_idx = 0\n",
    "            broken_cates = [x.split(\"/\")[-1] for x in glob.glob(f\"{class_dir / split}/*\")]\n",
    "            broken_cates.remove(\"good\")\n",
    "            for broken_cate in broken_cates:\n",
    "                image_paths = sorted(glob.glob(f\"{class_dir / split}/{broken_cate}/*.png\"))\n",
    "                for image_path in image_paths:\n",
    "                    new_name = image_path.split(\"/\")[:-1] + [f\"{broken_idx:03d}.png\"]\n",
    "                    new_name.remove(\"test\")\n",
    "                    new_name = \"/\".join(new_name)\n",
    "                    new_name = new_name.replace(broken_cate, \"broken\")\n",
    "                    new_name = new_name.replace(\"MVTEC\", \"MVTEC_det\")\n",
    "                    cmd = f\"cp {image_path} {new_name}\"\n",
    "                    os.system(cmd)\n",
    "\n",
    "                    mask_path = image_path.replace(\"test\", \"ground_truth\").replace(\".png\", \"_mask.png\")\n",
    "                    mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)\n",
    "                    contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n",
    "                    if not contours:\n",
    "                        raise ValueError(\"No contours found\")\n",
    "                    x, y, w, h = cv2.boundingRect(contours[0])\n",
    "                    bbox = [x, y, x + w, y + h]\n",
    "                    mvtech_ad_data_for_regression.append({\n",
    "                        \"image_path\": new_name,\n",
    "                        \"bbox\": bbox,\n",
    "                        \"class\": class_name,\n",
    "                        \"is_broken\": True,\n",
    "                        \"height\": mask.shape[0],\n",
    "                        \"width\": mask.shape[1]\n",
    "                    })\n",
    "\n",
    "                    broken_idx += 1\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5354"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(mvtech_ad_data_for_regression)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# shuffle the data\n",
    "\n",
    "import random\n",
    "random.seed(0)\n",
    "\n",
    "random.shuffle(mvtech_ad_data_for_regression)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "for data in mvtech_ad_data_for_regression:\n",
    "    data[\"image_path\"] = data[\"image_path\"].replace(\"MVTEC_det\", \".\")\n",
    "    data[\"bbox\"] = normalize_bbox(\n",
    "        bbox=data[\"bbox\"],\n",
    "        width=data[\"width\"],\n",
    "        height=data[\"height\"]\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"./MVTEC_det/mvtech_ad_data_for_regression.json\", \"w\") as f:\n",
    "    json.dump(mvtech_ad_data_for_regression, f, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Move all the images to the images folder\n",
    "\n",
    "os.makedirs(\"./MVTEC_det/images\", exist_ok=True)\n",
    "\n",
    "for class_name in class_names:\n",
    "    cmd = f\"mv MVTEC_det/{class_name} MVTEC_det/images/\"\n",
    "    os.system(cmd)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# split data into train test val\n",
    "train_ratio = 0.7\n",
    "val_ratio = 0.1\n",
    "test_ratio = 0.2\n",
    "\n",
    "train_data = mvtech_ad_data_for_regression[:int(len(mvtech_ad_data_for_regression) * train_ratio)]\n",
    "val_data = mvtech_ad_data_for_regression[int(len(mvtech_ad_data_for_regression) * train_ratio):int(len(mvtech_ad_data_for_regression) * (train_ratio + val_ratio))]\n",
    "test_data = mvtech_ad_data_for_regression[int(len(mvtech_ad_data_for_regression) * (train_ratio + val_ratio)):]\n",
    "\n",
    "\n",
    "\n",
    "with open(\"./MVTEC_det/train_data.json\", \"w\") as f:\n",
    "    json.dump(train_data, f, indent=4)\n",
    "\n",
    "with open(\"./MVTEC_det/val_data.json\", \"w\") as f:\n",
    "    json.dump(val_data, f, indent=4)\n",
    "\n",
    "with open(\"./MVTEC_det/test_data.json\", \"w\") as f:\n",
    "    json.dump(test_data, f, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Statistic the data balance of the train, val, test set between classes and between good and defect\n",
    "\n",
    "train_class_count = {class_name: 0 for class_name in class_names}\n",
    "train_good_defect_count = {\"good\": 0, \"defect\": 0}\n",
    "\n",
    "for data in train_data:\n",
    "    train_class_count[data[\"class\"]] += 1\n",
    "    if data[\"is_broken\"]:\n",
    "        train_good_defect_count[\"defect\"] += 1\n",
    "    else:\n",
    "        train_good_defect_count[\"good\"] += 1\n",
    "\n",
    "val_class_count = {class_name: 0 for class_name in class_names}\n",
    "val_good_defect_count = {\"good\": 0, \"defect\": 0}\n",
    "\n",
    "for data in val_data:\n",
    "    val_class_count[data[\"class\"]] += 1\n",
    "    if data[\"is_broken\"]:\n",
    "        val_good_defect_count[\"defect\"] += 1\n",
    "    else:\n",
    "        val_good_defect_count[\"good\"] += 1\n",
    "\n",
    "test_class_count = {class_name: 0 for class_name in class_names}\n",
    "test_good_defect_count = {\"good\": 0, \"defect\": 0}\n",
    "\n",
    "for data in test_data:\n",
    "    test_class_count[data[\"class\"]] += 1\n",
    "    if data[\"is_broken\"]:\n",
    "        test_good_defect_count[\"defect\"] += 1\n",
    "    else:\n",
    "        test_good_defect_count[\"good\"] += 1\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Good/Defect')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2000x2000 with 6 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot the data balance\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "fig, ax = plt.subplots(3, 2, figsize=(20, 20))\n",
    "\n",
    "ax[0, 0].bar(train_class_count.keys(), train_class_count.values())\n",
    "ax[0, 0].set_title(\"Train Class Count\")\n",
    "ax[0, 0].set_xlabel(\"Class\")\n",
    "\n",
    "ax[0, 1].bar(val_class_count.keys(), val_class_count.values())\n",
    "ax[0, 1].set_title(\"Val Class Count\")\n",
    "ax[0, 1].set_xlabel(\"Class\")\n",
    "\n",
    "ax[1, 0].bar(test_class_count.keys(), test_class_count.values())\n",
    "ax[1, 0].set_title(\"Test Class Count\")\n",
    "ax[1, 0].set_xlabel(\"Class\")\n",
    "\n",
    "ax[1, 1].bar(train_good_defect_count.keys(), train_good_defect_count.values())\n",
    "ax[1, 1].set_title(\"Train Good Defect Count\")\n",
    "ax[1, 1].set_xlabel(\"Good/Defect\")\n",
    "\n",
    "ax[2, 0].bar(val_good_defect_count.keys(), val_good_defect_count.values())\n",
    "ax[2, 0].set_title(\"Val Good Defect Count\")\n",
    "ax[2, 0].set_xlabel(\"Good/Defect\")\n",
    "\n",
    "ax[2, 1].bar(test_good_defect_count.keys(), test_good_defect_count.values())\n",
    "ax[2, 1].set_title(\"Test Good Defect Count\")\n",
    "ax[2, 1].set_xlabel(\"Good/Defect\")\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "minigptv",
   "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": "3.9.21"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}