DeepLSD_scale_bar_detection.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#DeepLSD model is taken from: https://github.com/cvg/DeepLSD\n",
    "\n",
    "import os\n",
    "import numpy as np\n",
    "import cv2\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.colors import LinearSegmentedColormap as lsc\n",
    "import torch\n",
    "\n",
    "from deeplsd.utils.tensor import batch_to_device\n",
    "from deeplsd.models.deeplsd_inference import DeepLSD\n",
    "from deeplsd.geometry.viz_2d import plot_images, plot_lines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "\n",
    "# Model config\n",
    "\n",
    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
    "conf = {\n",
    "    'detect_lines': True,  # Whether to detect lines or only DF/AF\n",
    "    'line_detection_params': {\n",
    "        'merge': False,  # Whether to merge close-by lines\n",
    "        'filtering': 'strict',  # Whether to filter out lines based on the DF/AF. Use 'strict' to get an even stricter filtering\n",
    "        'grad_thresh': 3,\n",
    "        'grad_nfa': True,  # If True, use the image gradient and the NFA score of LSD to further threshold lines. We recommand using it for easy images, but to turn it off for challenging images (e.g. night, foggy, blurry images)\n",
    "    }\n",
    "}\n",
    "\n",
    "# Load the model\n",
    "ckpt = './deeplsd_md.tar'\n",
    "ckpt = torch.load(str(ckpt), map_location='cpu')\n",
    "net = DeepLSD(conf)\n",
    "net.load_state_dict(ckpt['model'])\n",
    "net = net.to(device).eval()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from PIL import Image, ImageDraw, ImageFilter\n",
    "\n",
    "def detect_scalebar(path_image, thresh=0.5, isPlot=False):\n",
    "    \"\"\"\n",
    "    Detects all the line segments using DeepLSD algorithm\n",
    "\n",
    "    Args:\n",
    "        path_image (str): path of the image to analyse\n",
    "        thresh (float): angle threshold to determine if a segment is horizontal or not: it must in between 180+- thresh or 0+-thresh degrees\n",
    "        isPlot (bool): boolean to plot or not the image\n",
    "\n",
    "    Returns:\n",
    "        pred_SB (numpy array): 4 elements numpy array containing the [x1, y1, x2, y2] coordinates of the detected bar\n",
    "        indice_scalebar(int): indice of the line segment that is considered to be the scale bar\n",
    "    \"\"\"\n",
    "    \n",
    "\n",
    "    # Load an image\n",
    "    img = cv2.imread(path_image)[:, :, ::-1]\n",
    "    gray_img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)\n",
    "\n",
    "    # Detect (and optionally refine) the lines\n",
    "    inputs = {'image': torch.tensor(gray_img, dtype=torch.float, device=device)[None, None] / 255.}\n",
    "    with torch.no_grad():\n",
    "        out = net(inputs)\n",
    "        \n",
    "        pred_lines = out['lines'][0]\n",
    "\n",
    "    max = 0\n",
    "\n",
    "    s = pred_lines.shape\n",
    "    for i in range(s[0]):\n",
    "\n",
    "        vector = pred_lines[i][0] - pred_lines[i][1]\n",
    "        \n",
    "        # Calculate the angle in radians\n",
    "        angle_radians = np.arctan2(vector[1], vector[0])\n",
    "        \n",
    "        # Convert to degrees\n",
    "        angle_degrees = np.degrees(angle_radians)\n",
    "\n",
    "        if abs(angle_degrees) < thresh or abs(angle_degrees) > 180-thresh:\n",
    "            v = pred_lines[i][1] - pred_lines[i][0] \n",
    "            distance = np.linalg.norm(v)\n",
    "            if distance > max:\n",
    "                max = distance\n",
    "                pred_SB = pred_lines[i]\n",
    "                indice_scalebar = i\n",
    "\n",
    "    x1 = np.min([pred_SB[0][0],pred_SB[1][0]])\n",
    "    y1 = np.mean([pred_SB[0][1],pred_SB[1][1]])\n",
    "\n",
    "    x2 = np.max([pred_SB[0][0],pred_SB[1][0]])\n",
    "    y2 = y1\n",
    "\n",
    "    pred_SB =np.array([x1, y1, x2, y2])\n",
    "    if isPlot:  \n",
    "        shape = [(x1, y1),(x2, y2+5)] \n",
    "        Im_color = Image.open(path_image)\n",
    "        img1 = ImageDraw.Draw(Im_color) \n",
    "        img1.rectangle(shape, fill=\"green\", outline =\"green\")\n",
    "        Im_color.show() \n",
    "\n",
    "    return pred_SB, indice_scalebar\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ant</th>\n",
       "      <th>x1_lmk</th>\n",
       "      <th>y1_lmk</th>\n",
       "      <th>x2_lmk</th>\n",
       "      <th>y2_lmk</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>anic32-900190-1_p_1.jpg</td>\n",
       "      <td>190.603985</td>\n",
       "      <td>199.479713</td>\n",
       "      <td>407.313962</td>\n",
       "      <td>328.349297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>antweb1008066_p_1.jpg</td>\n",
       "      <td>175.484684</td>\n",
       "      <td>109.914697</td>\n",
       "      <td>397.234428</td>\n",
       "      <td>170.986006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>antweb1008086_p_1.jpg</td>\n",
       "      <td>174.224742</td>\n",
       "      <td>117.000933</td>\n",
       "      <td>384.635011</td>\n",
       "      <td>197.457880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>antweb1038001_p_1.jpg</td>\n",
       "      <td>137.686432</td>\n",
       "      <td>91.142189</td>\n",
       "      <td>388.414836</td>\n",
       "      <td>215.302585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>antweb1038003_p_1.jpg</td>\n",
       "      <td>107.447831</td>\n",
       "      <td>71.837948</td>\n",
       "      <td>287.619498</td>\n",
       "      <td>114.624509</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       ant      x1_lmk      y1_lmk      x2_lmk      y2_lmk\n",
       "0  anic32-900190-1_p_1.jpg  190.603985  199.479713  407.313962  328.349297\n",
       "1    antweb1008066_p_1.jpg  175.484684  109.914697  397.234428  170.986006\n",
       "2    antweb1008086_p_1.jpg  174.224742  117.000933  384.635011  197.457880\n",
       "3    antweb1038001_p_1.jpg  137.686432   91.142189  388.414836  215.302585\n",
       "4    antweb1038003_p_1.jpg  107.447831   71.837948  287.619498  114.624509"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import os \n",
    "import csv\n",
    "\n",
    "test_folder = \"./thorax_dataset/images/test/\"\n",
    "test_folder = \"/Users/vivien.gaillet/Library/CloudStorage/OneDrive-NordAngliaEducation/NAE - Files/Downloads/original/\"\n",
    "\n",
    "csv_file_name = \"thorax_only.csv\"\n",
    "\n",
    "#create new directory\n",
    "new_dir_location = \"./thorax_dataset/images/\"\n",
    "directory_name = \"results_scale_bar/\"\n",
    "path_directory_save = os.path.join(\"./thorax_dataset/images/\", directory_name)\n",
    "\n",
    "# Create the directory if it doesn't exist\n",
    "if not os.path.exists(path_directory_save):\n",
    "    os.makedirs(path_directory_save)\n",
    "\n",
    "#create saving files \n",
    "\n",
    "path_detected_bounding_box_csv = \"./result_scale_bar_bounding_box.csv\"\n",
    "\n",
    "with open(path_detected_bounding_box_csv, mode='w', newline='') as file:\n",
    "    writer = csv.writer(file)\n",
    "    writer.writerow([\"ant\", \"x1_scalebar\",\"y1_scalebar\", \"x2_scalebar\", \"y2_scalebar\"])\n",
    "\n",
    "df = pd.read_csv(csv_file_name)\n",
    "df.head()\n",
    "\n",
    "# List all image file names inside the folder\n",
    "image_files = set(os.listdir(test_folder))\n",
    "\n",
    "# Filter the DataFrame to retain only rows with filenames in the folder\n",
    "filtered_df = df[df['ant'].isin(image_files)]\n",
    "filtered_df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/Users/vivien.gaillet/Library/CloudStorage/OneDrive-NordAngliaEducation/NAE - Files/Downloads/original/anic32-900190-1_p_1.jpg\n",
      "[213.99808 588.8345  460.00162 588.8345 ]\n",
      "['anic32-900190-1_p_1.jpg', 213.99808, 586.83447265625, 460.00162, 590.83447265625]\n",
      "/Users/vivien.gaillet/Library/CloudStorage/OneDrive-NordAngliaEducation/NAE - Files/Downloads/original/antweb1008066_p_1.jpg\n",
      "[ 920.99927  781.77    1087.9993   781.77   ]\n",
      "['antweb1008066_p_1.jpg', 920.99927, 779.77001953125, 1087.9993, 783.77001953125]\n",
      "/Users/vivien.gaillet/Library/CloudStorage/OneDrive-NordAngliaEducation/NAE - Files/Downloads/original/antweb1008086_p_1.jpg\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[9], line 6\u001b[0m\n\u001b[1;32m      4\u001b[0m path \u001b[38;5;241m=\u001b[39m test_folder \u001b[38;5;241m+\u001b[39m img\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28mprint\u001b[39m(path)\n\u001b[0;32m----> 6\u001b[0m scalebar, i \u001b[38;5;241m=\u001b[39m \u001b[43mdetect_scalebar\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mthresh\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.5\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      7\u001b[0m \u001b[38;5;28mprint\u001b[39m(scalebar)\n\u001b[1;32m      9\u001b[0m Im_color \u001b[38;5;241m=\u001b[39m Image\u001b[38;5;241m.\u001b[39mopen(path)\n",
      "Cell \u001b[0;32mIn[4], line 25\u001b[0m, in \u001b[0;36mdetect_scalebar\u001b[0;34m(path_image, thresh, isPlot)\u001b[0m\n\u001b[1;32m     23\u001b[0m inputs \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mimage\u001b[39m\u001b[38;5;124m'\u001b[39m: torch\u001b[38;5;241m.\u001b[39mtensor(gray_img, dtype\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\u001b[39mfloat, device\u001b[38;5;241m=\u001b[39mdevice)[\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;28;01mNone\u001b[39;00m] \u001b[38;5;241m/\u001b[39m \u001b[38;5;241m255.\u001b[39m}\n\u001b[1;32m     24\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mno_grad():\n\u001b[0;32m---> 25\u001b[0m     out \u001b[38;5;241m=\u001b[39m \u001b[43mnet\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     27\u001b[0m     pred_lines \u001b[38;5;241m=\u001b[39m out[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlines\u001b[39m\u001b[38;5;124m'\u001b[39m][\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m     29\u001b[0m \u001b[38;5;28mmax\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1530\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   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\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/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1536\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   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1538\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   1539\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   1540\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-> 1541\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   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/LETR/DeepLSD/deeplsd/models/base_model.py:71\u001b[0m, in \u001b[0;36mBaseModel.forward\u001b[0;34m(self, data)\u001b[0m\n\u001b[1;32m     69\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequired_data_keys:\n\u001b[1;32m     70\u001b[0m     \u001b[38;5;28;01massert\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m data, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mMissing key \u001b[39m\u001b[38;5;132;01m{}\u001b[39;00m\u001b[38;5;124m in data\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mformat(key)\n\u001b[0;32m---> 71\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[43mdata\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/LETR/DeepLSD/deeplsd/models/deeplsd_inference.py:78\u001b[0m, in \u001b[0;36mDeepLSD._forward\u001b[0;34m(self, data)\u001b[0m\n\u001b[1;32m     76\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mms_forward(data)\n\u001b[1;32m     77\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 78\u001b[0m     base \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbackbone\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mimage\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     80\u001b[0m     \u001b[38;5;66;03m# DF prediction\u001b[39;00m\n\u001b[1;32m     81\u001b[0m     outputs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdf_norm\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdf_head(base)\u001b[38;5;241m.\u001b[39msqueeze(\u001b[38;5;241m1\u001b[39m)\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1530\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   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\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/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1536\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   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1538\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   1539\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   1540\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-> 1541\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   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/LETR/DeepLSD/deeplsd/models/backbones/vgg_unet.py:93\u001b[0m, in \u001b[0;36mVGGUNet.forward\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m     90\u001b[0m out \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdeblock4(features[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m])\n\u001b[1;32m     91\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m deblock, feat \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(\n\u001b[1;32m     92\u001b[0m     [\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdeblock3, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdeblock2, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdeblock1], features[:\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m][::\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]):\n\u001b[0;32m---> 93\u001b[0m     out \u001b[38;5;241m=\u001b[39m \u001b[43mdeblock\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcat\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\n\u001b[1;32m     94\u001b[0m \u001b[43m        \u001b[49m\u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minterpolate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mout\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfeat\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshape\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m:\u001b[49m\u001b[38;5;241;43m4\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mbilinear\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     95\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfeat\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdim\u001b[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     97\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m out\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1530\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   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\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/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1536\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   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1538\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   1539\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   1540\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-> 1541\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   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/container.py:217\u001b[0m, in \u001b[0;36mSequential.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    215\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m):\n\u001b[1;32m    216\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m module \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m:\n\u001b[0;32m--> 217\u001b[0m         \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m    218\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28minput\u001b[39m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1530\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   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\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/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1536\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   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1538\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   1539\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   1540\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-> 1541\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   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/conv.py:460\u001b[0m, in \u001b[0;36mConv2d.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    459\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 460\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_conv_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/modules/conv.py:456\u001b[0m, in \u001b[0;36mConv2d._conv_forward\u001b[0;34m(self, input, weight, bias)\u001b[0m\n\u001b[1;32m    452\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpadding_mode \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mzeros\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m    453\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m F\u001b[38;5;241m.\u001b[39mconv2d(F\u001b[38;5;241m.\u001b[39mpad(\u001b[38;5;28minput\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reversed_padding_repeated_twice, mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpadding_mode),\n\u001b[1;32m    454\u001b[0m                     weight, bias, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstride,\n\u001b[1;32m    455\u001b[0m                     _pair(\u001b[38;5;241m0\u001b[39m), \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdilation, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgroups)\n\u001b[0;32m--> 456\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconv2d\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbias\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstride\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    457\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpadding\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdilation\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgroups\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "\"\"\"\n",
    "Detects the scale bars for all the images in the testing set,\n",
    "and store the images of the detected scaler bar in \"./thorax_dataset/images/results_scale_bar/\"\n",
    "and the bounding box pixel values in \"./result_scale_bar_bounding_box.csv\"\n",
    "\"\"\"\n",
    "for i, img in enumerate(filtered_df.iloc[:, 0]):            \n",
    "    path = test_folder + img\n",
    "    print(path)\n",
    "    scalebar, i = detect_scalebar(path, thresh=0.5)\n",
    "    print(scalebar)\n",
    "    \n",
    "    Im_color = Image.open(path)\n",
    "    img1 = ImageDraw.Draw(Im_color) \n",
    "    t = 10\n",
    "    shape = [(scalebar[0], scalebar[1]-t),(scalebar[0]+t, scalebar[1])] \n",
    "    img1.rectangle(shape, fill=\"red\", outline =\"red\")\n",
    "\n",
    "    shape = [(scalebar[2]-t, scalebar[3]+10),(scalebar[2], scalebar[3]+10+t)] \n",
    "    img1.rectangle(shape, fill=\"red\", outline =\"red\")\n",
    "\n",
    "    Im_color.save(path_directory_save + \"scale_bar_\" + img)\n",
    "    Im_color.close() \n",
    "\n",
    "    t = 2\n",
    "    new_row_csv = [img, scalebar[0],scalebar[1]-t,scalebar[2],scalebar[3]+t]\n",
    "    print(new_row_csv)\n",
    "    with open(path_detected_bounding_box_csv, mode='a', newline='') as file:\n",
    "        writer = csv.writer(file)\n",
    "        # Write the row\n",
    "        writer.writerow(new_row_csv)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}