[+] Add first analysis

data/train/labels/0265.csv

 198,331,450,543,ceder
-475,567,563,661,interdiction

data/train/labels/0751.csv

-297,185,352,367,fvert
-276,609,303,690,fvert

machine_learning/learn.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Entrainement d'un modèle avec la méthode des SVM"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Chargement des données d'entrainement"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import cv2\n",
+    "import numpy as np\n",
+    "import random"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\" \n",
+    "We will create a dict with all the usefull datas of the training dataset\n",
+    "datas = {\n",
+    "    \"XXXX\" (name of the file) : {\n",
+    "        \"img\" : ndarray of the image,\n",
+    "        \"labels\" (data of the labels): {\n",
+    "            \"X\" index of the label (0,1,...,n) : {\n",
+    "                \"name\" : name of the label,\n",
+    "                \"coord\" : coord of the label like xmin, ymin, xmax, ymax,\n",
+    "                \"img\" : crooped img of the label,\n",
+    "            }\n",
+    "        }\n",
+    "    }\n",
+    "}\n",
+    "\n",
+    "\"\"\"\n",
+    "\n",
+    "def generate_empty_bbox(image_width, image_height):\n",
+    "    # Thanks to the stats, we know that size of bbox will be (127, 145) -> Average size of labels \n",
+    "    # Génération de coordonnées aléatoires pour le coin supérieur gauche de la boundebox\n",
+    "    x_min = random.randint(0, image_width - 127)\n",
+    "    y_min = random.randint(0, image_height - 145)\n",
+    "    \n",
+    "    # Calcul des coordonnées du coin inférieur droit de la boundebox\n",
+    "    x_max = x_min + 127\n",
+    "    y_max = y_min + 145\n",
+    "    \n",
+    "    return (x_min, y_min, x_max, y_max)\n",
+    "\n",
+    "def load_data(image_dir, label_dir):\n",
+    "    datas = {}\n",
+    "\n",
+    "    for image_file in os.listdir(image_dir):\n",
+    "        # Computing name and files paths\n",
+    "        image_path = image_dir + '/' + image_file\n",
+    "        name = image_file.split('.')[0]\n",
+    "        label_path = label_dir + '/' + name + '.csv'\n",
+    "        \n",
+    "        # Import image as array\n",
+    "        image = cv2.imread(image_path)\n",
+    "\n",
+    "        # Import labels as array \n",
+    "        with open(label_path, 'r') as file:\n",
+    "            rows = file.readlines()\n",
+    "\n",
+    "            label_data = {}\n",
+    "            if rows == ['\\n']:  # Create a random empty label to balance model\n",
+    "                # Create random coords for empty label\n",
+    "                xmin, ymin, xmax, ymax = generate_empty_bbox(image.shape[1], image.shape[0])\n",
+    "    \n",
+    "                # Get the cropped image (as array) of the label\n",
+    "                cropped_image = image[ymin:ymax, xmin:xmax]\n",
+    "               \n",
+    "                label_data[0] = {\n",
+    "                        \"name\":\"empty\",\n",
+    "                        \"coord\": (xmin, ymin, xmax, ymax),\n",
+    "                        \"img\":cropped_image\n",
+    "                    }\n",
+    "            else:\n",
+    "                for i, row in enumerate(rows):  # One image can contain several labels\n",
+    "                    row = row.strip().split(\",\")\n",
+    "\n",
+    "                    # Compute coords of the label\n",
+    "                    xmin, ymin, xmax, ymax = map(int, row[0:4])\n",
+    "\n",
+    "                    # Get the label name\n",
+    "                    class_name = row[4]\n",
+    "\n",
+    "                    # Get the cropped image (as array) of the label\n",
+    "                    cropped_image = image[ymin:ymax, xmin:xmax]\n",
+    "                    \n",
+    "                    # Adding to the json\n",
+    "                    label_data[i] = {\n",
+    "                        \"name\":class_name,\n",
+    "                        \"coord\": (xmin, ymin, xmax, ymax),\n",
+    "                        \"img\":cropped_image\n",
+    "                    }\n",
+    "\n",
+    "        datas[name] = {\n",
+    "             \"img\" : image,\n",
+    "             \"labels\" : label_data,\n",
+    "        }\n",
+    "       \n",
+    "    return datas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Creating the dict of the datas \n",
+    "\n",
+    "datas = load_data(\"../data/train/images\", \"../data/train/labels\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def extract_features(img):\n",
+    "    # Convertion to gray level\n",
+    "    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n",
+    "\n",
+    "    # Color Hist\n",
+    "    hist_color = cv2.calcHist([img], [0, 1, 2], None, [8, 8, 8], [0, 256, 0, 256, 0, 256])\n",
+    "    hist_color = cv2.normalize(hist_color, hist_color).flatten()\n",
+    "    \n",
+    "    # Gradient Hist\n",
+    "    sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=5)\n",
+    "    sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=5)\n",
+    "    grad_mag = np.sqrt(sobelx**2 + sobely**2)\n",
+    "    hist_gradient = cv2.calcHist([grad_mag.astype(np.uint8)], [0], None, [16], [0, 256])\n",
+    "    hist_gradient = cv2.normalize(hist_gradient, hist_gradient).flatten()\n",
+    "    \n",
+    "    return np.concatenate((hist_color, hist_gradient))\n",
+    "\n",
+    "\n",
+    "# Dict to convert str class name to int\n",
+    "name_to_int = {\n",
+    "    \"danger\": 0,\n",
+    "    \"interdiction\": 1,\n",
+    "    \"obligation\": 2,\n",
+    "    \"stop\": 3,\n",
+    "    \"ceder\": 4,\n",
+    "    \"frouge\": 5,\n",
+    "    \"forange\": 6,\n",
+    "    \"fvert\": 7,\n",
+    "    \"ff\": 8,\n",
+    "    \"empty\": 9\n",
+    "}\n",
+    "\n",
+    "\n",
+    "# Creating arrays with all labels datas & classes\n",
+    "X_train = []\n",
+    "Y_train = []\n",
+    "\n",
+    "for name, data in datas.items():\n",
+    "    for row in data[\"labels\"].values():\n",
+    "        X_train.append(extract_features(row[\"img\"]))\n",
+    "        Y_train.append(name_to_int[row[\"name\"]])\n",
+    "\n",
+    "X_train = np.array(X_train)\n",
+    "Y_train = np.array(Y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1 1 0 ... 1 5 7]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn import svm\n",
+    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n",
+    "\n",
+    "svm_model = svm.SVC(kernel='linear')  # Choix du noyau linéaire\n",
+    "svm_model.fit(X_train, Y_train)\n",
+    "\n",
+    "print(svm_model)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "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": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}