{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "KQaA6Onj_yBX"
   },
   "source": [
    "## 1. charger le dataset PyroSDIS"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "URzTGYqSqQFe"
   },
   "source": [
    "pyronear/pyro-sdis dataset  \n",
    "https://huggingface.co/datasets/pyronear/pyro-sdis/viewer/default/train?p=2&views%5B%5D=val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "XUQxOaFUp0cm"
   },
   "outputs": [],
   "source": [
    "from datasets import load_dataset\n",
    "raw_data = load_dataset(\"pyronear/pyro-sdis\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UKaqfIecBMBc"
   },
   "source": [
    "train = 29 537 images\n",
    "\n",
    "val = 4 099 images"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "7SvQAhRZBoha"
   },
   "source": [
    "## 2. afficher quelques images pour vérifier et compter les classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "J-IhONzcB0cV"
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import random\n",
    "\n",
    "raw_train_data = raw_data[\"train\"]\n",
    "raw_val_data = raw_data[\"val\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 159
    },
    "executionInfo": {
     "elapsed": 2325,
     "status": "ok",
     "timestamp": 1763118704403,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "KsHrGWzICk9R",
    "outputId": "087e847b-71d2-4037-bd85-b4c022a48e8e"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x800 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15, 8))                             # taille du \"canvas\" des images\n",
    "\n",
    "for i in range(5):                                      # on veut afficher 5 images\n",
    "    index = random.randint(0, len(raw_train_data) - 1)  # choisir une image aléatoire\n",
    "    sample = raw_train_data[index]                      # récupérer l'exemple\n",
    "    img = sample[\"image\"]                               # c'est une image PIL directement utilisable\n",
    "    ann = sample[\"annotations\"]                         # les annotations (vide = no fire)\n",
    "\n",
    "    # Sous-plot\n",
    "    plt.subplot(1, 5, i + 1)                            # 1 ligne, 5 colonnes, image n°i+1\n",
    "    plt.imshow(img)                                     # afficher l'image\n",
    "    plt.axis(\"off\")                                     # enlever les axes\n",
    "    plt.title(\"FIRE\" if ann != \"\" else \"NO FIRE\")       # afficher le label\n",
    "\n",
    "plt.show()                                              # afficher toutes les images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 159
    },
    "executionInfo": {
     "elapsed": 2541,
     "status": "ok",
     "timestamp": 1763118706946,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "2Ugy33bODO_j",
    "outputId": "ee37ac28-b513-4af0-fdf6-b5fc7e953520"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x800 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15, 8))                             # taille du \"canvas\" des images\n",
    "\n",
    "for i in range(5):                                      # on veut afficher 5 images\n",
    "    index = random.randint(0, len(raw_val_data) - 1)    # choisir une image aléatoire\n",
    "    sample = raw_val_data[index]                        # récupérer l'exemple\n",
    "    img = sample[\"image\"]                               # c'est une image PIL directement utilisable\n",
    "    ann = sample[\"annotations\"]                         # les annotations (vide = no fire)\n",
    "\n",
    "    # Sous-plot\n",
    "    plt.subplot(1, 5, i + 1)                            # 1 ligne, 5 colonnes, image n°i+1\n",
    "    plt.imshow(img)                                     # afficher l'image\n",
    "    plt.axis(\"off\")                                     # enlever les axes\n",
    "    plt.title(\"FIRE\" if ann != \"\" else \"NO FIRE\")       # afficher le label\n",
    "\n",
    "plt.show()                                              # afficher toutes les images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 125
    },
    "executionInfo": {
     "elapsed": 220059,
     "status": "ok",
     "timestamp": 1763118927007,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "ruhjpk7yFyhu",
    "outputId": "3ca3475c-9e61-42f1-a8f9-4169048c65ab"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"df_counts\",\n  \"rows\": 2,\n  \"fields\": [\n    {\n      \"column\": \"split\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"val\",\n          \"train\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"fire\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 15165,\n        \"min\": 3345,\n        \"max\": 24792,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          3345,\n          24792\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"no_fire\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2822,\n        \"min\": 754,\n        \"max\": 4745,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          754,\n          4745\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"total\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 17987,\n        \"min\": 4099,\n        \"max\": 29537,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          4099,\n          29537\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe",
       "variable_name": "df_counts"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-a600d65f-ea51-4b10-b46b-52f3564fb073\" class=\"colab-df-container\">\n",
       "    <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>split</th>\n",
       "      <th>fire</th>\n",
       "      <th>no_fire</th>\n",
       "      <th>total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>train</td>\n",
       "      <td>24792</td>\n",
       "      <td>4745</td>\n",
       "      <td>29537</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>val</td>\n",
       "      <td>3345</td>\n",
       "      <td>754</td>\n",
       "      <td>4099</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a600d65f-ea51-4b10-b46b-52f3564fb073')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-a600d65f-ea51-4b10-b46b-52f3564fb073 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-a600d65f-ea51-4b10-b46b-52f3564fb073');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "    <div id=\"df-a1d378e7-60c4-4717-94bf-c123f29a4e7b\">\n",
       "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-a1d378e7-60c4-4717-94bf-c123f29a4e7b')\"\n",
       "                title=\"Suggest charts\"\n",
       "                style=\"display:none;\">\n",
       "\n",
       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "     width=\"24px\">\n",
       "    <g>\n",
       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
       "    </g>\n",
       "</svg>\n",
       "      </button>\n",
       "\n",
       "<style>\n",
       "  .colab-df-quickchart {\n",
       "      --bg-color: #E8F0FE;\n",
       "      --fill-color: #1967D2;\n",
       "      --hover-bg-color: #E2EBFA;\n",
       "      --hover-fill-color: #174EA6;\n",
       "      --disabled-fill-color: #AAA;\n",
       "      --disabled-bg-color: #DDD;\n",
       "  }\n",
       "\n",
       "  [theme=dark] .colab-df-quickchart {\n",
       "      --bg-color: #3B4455;\n",
       "      --fill-color: #D2E3FC;\n",
       "      --hover-bg-color: #434B5C;\n",
       "      --hover-fill-color: #FFFFFF;\n",
       "      --disabled-bg-color: #3B4455;\n",
       "      --disabled-fill-color: #666;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart {\n",
       "    background-color: var(--bg-color);\n",
       "    border: none;\n",
       "    border-radius: 50%;\n",
       "    cursor: pointer;\n",
       "    display: none;\n",
       "    fill: var(--fill-color);\n",
       "    height: 32px;\n",
       "    padding: 0;\n",
       "    width: 32px;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart:hover {\n",
       "    background-color: var(--hover-bg-color);\n",
       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "    fill: var(--button-hover-fill-color);\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart-complete:disabled,\n",
       "  .colab-df-quickchart-complete:disabled:hover {\n",
       "    background-color: var(--disabled-bg-color);\n",
       "    fill: var(--disabled-fill-color);\n",
       "    box-shadow: none;\n",
       "  }\n",
       "\n",
       "  .colab-df-spinner {\n",
       "    border: 2px solid var(--fill-color);\n",
       "    border-color: transparent;\n",
       "    border-bottom-color: var(--fill-color);\n",
       "    animation:\n",
       "      spin 1s steps(1) infinite;\n",
       "  }\n",
       "\n",
       "  @keyframes spin {\n",
       "    0% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "      border-left-color: var(--fill-color);\n",
       "    }\n",
       "    20% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    30% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    40% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    60% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    80% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "    90% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "  }\n",
       "</style>\n",
       "\n",
       "      <script>\n",
       "        async function quickchart(key) {\n",
       "          const quickchartButtonEl =\n",
       "            document.querySelector('#' + key + ' button');\n",
       "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
       "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
       "          try {\n",
       "            const charts = await google.colab.kernel.invokeFunction(\n",
       "                'suggestCharts', [key], {});\n",
       "          } catch (error) {\n",
       "            console.error('Error during call to suggestCharts:', error);\n",
       "          }\n",
       "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
       "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
       "        }\n",
       "        (() => {\n",
       "          let quickchartButtonEl =\n",
       "            document.querySelector('#df-a1d378e7-60c4-4717-94bf-c123f29a4e7b button');\n",
       "          quickchartButtonEl.style.display =\n",
       "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "        })();\n",
       "      </script>\n",
       "    </div>\n",
       "\n",
       "  <div id=\"id_175123dc-df5b-4e0d-9295-05bbaae6fd03\">\n",
       "    <style>\n",
       "      .colab-df-generate {\n",
       "        background-color: #E8F0FE;\n",
       "        border: none;\n",
       "        border-radius: 50%;\n",
       "        cursor: pointer;\n",
       "        display: none;\n",
       "        fill: #1967D2;\n",
       "        height: 32px;\n",
       "        padding: 0 0 0 0;\n",
       "        width: 32px;\n",
       "      }\n",
       "\n",
       "      .colab-df-generate:hover {\n",
       "        background-color: #E2EBFA;\n",
       "        box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "        fill: #174EA6;\n",
       "      }\n",
       "\n",
       "      [theme=dark] .colab-df-generate {\n",
       "        background-color: #3B4455;\n",
       "        fill: #D2E3FC;\n",
       "      }\n",
       "\n",
       "      [theme=dark] .colab-df-generate:hover {\n",
       "        background-color: #434B5C;\n",
       "        box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "        filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "        fill: #FFFFFF;\n",
       "      }\n",
       "    </style>\n",
       "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('df_counts')\"\n",
       "            title=\"Generate code using this dataframe.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "       width=\"24px\">\n",
       "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "    <script>\n",
       "      (() => {\n",
       "      const buttonEl =\n",
       "        document.querySelector('#id_175123dc-df5b-4e0d-9295-05bbaae6fd03 button.colab-df-generate');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      buttonEl.onclick = () => {\n",
       "        google.colab.notebook.generateWithVariable('df_counts');\n",
       "      }\n",
       "      })();\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   split   fire  no_fire  total\n",
       "0  train  24792     4745  29537\n",
       "1    val   3345      754   4099"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 1) Import des librairies\n",
    "# -----------------------------------------------------------\n",
    "import pandas as pd   # pour afficher un tableau propre\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 2) Fonction qui compte fire/no_fire dans un split\n",
    "# -----------------------------------------------------------\n",
    "def count_fire_no_fire(dataset_split):\n",
    "    \"\"\"\n",
    "    dataset_split : raw_data[\"train\"] ou raw_data[\"val\"]\n",
    "    fire = annotations non vide\n",
    "    no_fire = annotations vide\n",
    "    \"\"\"\n",
    "\n",
    "    fire_count = 0\n",
    "    no_fire_count = 0\n",
    "\n",
    "    # parcourir chaque ligne du dataset\n",
    "    for sample in dataset_split:\n",
    "        if sample[\"annotations\"] != \"\":     # annotation non vide = FIRE\n",
    "            fire_count += 1\n",
    "        else:                               # annotation vide = NO_FIRE\n",
    "            no_fire_count += 1\n",
    "\n",
    "    return fire_count, no_fire_count\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 3) Calculer les valeurs pour train et val\n",
    "# -----------------------------------------------------------\n",
    "train_fire, train_no_fire = count_fire_no_fire(raw_train_data)\n",
    "val_fire, val_no_fire     = count_fire_no_fire(raw_val_data)\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 4) Construire un petit tableau sous forme de DataFrame\n",
    "# -----------------------------------------------------------\n",
    "df_counts = pd.DataFrame({\n",
    "    \"split\": [\"train\", \"val\"],\n",
    "    \"fire\": [train_fire, val_fire],\n",
    "    \"no_fire\": [train_no_fire, val_no_fire],\n",
    "    \"total\": [train_fire + train_no_fire, val_fire + val_no_fire]\n",
    "})\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 5) Afficher le tableau proprement\n",
    "# -----------------------------------------------------------\n",
    "df_counts\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0vCXjzNdB1Bb"
   },
   "source": [
    "## 3. création de la cible fire/no_fire (0/1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "ijmkT3-dB8FE"
   },
   "outputs": [],
   "source": [
    "def add_target(example):\n",
    "    if example[\"annotations\"] != \"\":\n",
    "        example[\"target\"] = 1     # il y a une annotation → FIRE\n",
    "    else:\n",
    "        example[\"target\"] = 0     # annotation vide → NO FIRE\n",
    "    return example\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 9,
     "status": "ok",
     "timestamp": 1763118927010,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "IJdQxZMXJInS",
    "outputId": "982ad03b-29df-47fc-d138-5f5594c128da"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatasetDict({\n",
       "    train: Dataset({\n",
       "        features: ['image', 'annotations', 'image_name', 'partner', 'camera', 'date', 'target'],\n",
       "        num_rows: 29537\n",
       "    })\n",
       "    val: Dataset({\n",
       "        features: ['image', 'annotations', 'image_name', 'partner', 'camera', 'date', 'target'],\n",
       "        num_rows: 4099\n",
       "    })\n",
       "})"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "raw_data_target = raw_data.map(add_target)\n",
    "raw_data_target\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 19,
     "status": "ok",
     "timestamp": 1763118927031,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "0CgwkWf9LEhY",
    "outputId": "93add31b-b5c1-403a-ccba-2a13423a111c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['image', 'annotations', 'image_name', 'partner', 'camera', 'date', 'target']"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "raw_data_target['train'].column_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 6,
     "status": "ok",
     "timestamp": 1763118927052,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "soawAqxgLNiF",
    "outputId": "70b066ba-6819-4b3e-8743-cec3d35d1c00"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=1280x720>,\n",
       " 'annotations': '1 0.0670989 0.708931 0.134198 0.108047',\n",
       " 'image_name': 'sdis-07_brison-200_2024-01-15T14-32-36.jpg',\n",
       " 'partner': 'sdis-07',\n",
       " 'camera': 'brison-200',\n",
       " 'date': '2024-01-15T14-32-36',\n",
       " 'target': 1}"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "raw_data_target['train'][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 6,
     "status": "ok",
     "timestamp": 1763118927080,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "1rVGjnS-LSzF",
    "outputId": "a35e9e3d-7c53-4fc8-aed0-1e8f325884bb"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=1280x720>,\n",
       " 'annotations': '1 0.953115 0.888229 0.044361899999999954 0.04581269999999993\\n1 0.317477 0.545627 0.02168020000000004 0.01992729999999998',\n",
       " 'image_name': 'force-06_courmettes-160_2024-01-08T12-44-06.jpg',\n",
       " 'partner': 'force-06',\n",
       " 'camera': 'courmettes-160',\n",
       " 'date': '2024-01-08T12-44-06',\n",
       " 'target': 1}"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "raw_data_target['val'][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 112
    },
    "executionInfo": {
     "elapsed": 512,
     "status": "ok",
     "timestamp": 1763118927613,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "XTIfm71ZMNqQ",
    "outputId": "27b92fec-79bc-4ffe-8c30-b34a2144786b"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "summary": "{\n  \"name\": \"})\",\n  \"rows\": 2,\n  \"fields\": [\n    {\n      \"column\": \"split\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"val\",\n          \"train\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"fire (1)\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 15165,\n        \"min\": 3345,\n        \"max\": 24792,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          3345,\n          24792\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"no_fire (0)\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2822,\n        \"min\": 754,\n        \"max\": 4745,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          754,\n          4745\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"total\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 17987,\n        \"min\": 4099,\n        \"max\": 29537,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          4099,\n          29537\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"% fire\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.6475588001646544,\n        \"min\": 81.61,\n        \"max\": 83.94,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          81.61,\n          83.94\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"% no_fire\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.647558800164657,\n        \"min\": 16.06,\n        \"max\": 18.39,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          18.39,\n          16.06\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
       "type": "dataframe"
      },
      "text/html": [
       "\n",
       "  <div id=\"df-4c502061-d028-4a13-ba9d-4771e3115907\" class=\"colab-df-container\">\n",
       "    <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>split</th>\n",
       "      <th>fire (1)</th>\n",
       "      <th>no_fire (0)</th>\n",
       "      <th>total</th>\n",
       "      <th>% fire</th>\n",
       "      <th>% no_fire</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>train</td>\n",
       "      <td>24792</td>\n",
       "      <td>4745</td>\n",
       "      <td>29537</td>\n",
       "      <td>83.94</td>\n",
       "      <td>16.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>val</td>\n",
       "      <td>3345</td>\n",
       "      <td>754</td>\n",
       "      <td>4099</td>\n",
       "      <td>81.61</td>\n",
       "      <td>18.39</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4c502061-d028-4a13-ba9d-4771e3115907')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-4c502061-d028-4a13-ba9d-4771e3115907 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-4c502061-d028-4a13-ba9d-4771e3115907');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "    <div id=\"df-c1ba6420-8195-4d84-b330-88df6a18027c\">\n",
       "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-c1ba6420-8195-4d84-b330-88df6a18027c')\"\n",
       "                title=\"Suggest charts\"\n",
       "                style=\"display:none;\">\n",
       "\n",
       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "     width=\"24px\">\n",
       "    <g>\n",
       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
       "    </g>\n",
       "</svg>\n",
       "      </button>\n",
       "\n",
       "<style>\n",
       "  .colab-df-quickchart {\n",
       "      --bg-color: #E8F0FE;\n",
       "      --fill-color: #1967D2;\n",
       "      --hover-bg-color: #E2EBFA;\n",
       "      --hover-fill-color: #174EA6;\n",
       "      --disabled-fill-color: #AAA;\n",
       "      --disabled-bg-color: #DDD;\n",
       "  }\n",
       "\n",
       "  [theme=dark] .colab-df-quickchart {\n",
       "      --bg-color: #3B4455;\n",
       "      --fill-color: #D2E3FC;\n",
       "      --hover-bg-color: #434B5C;\n",
       "      --hover-fill-color: #FFFFFF;\n",
       "      --disabled-bg-color: #3B4455;\n",
       "      --disabled-fill-color: #666;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart {\n",
       "    background-color: var(--bg-color);\n",
       "    border: none;\n",
       "    border-radius: 50%;\n",
       "    cursor: pointer;\n",
       "    display: none;\n",
       "    fill: var(--fill-color);\n",
       "    height: 32px;\n",
       "    padding: 0;\n",
       "    width: 32px;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart:hover {\n",
       "    background-color: var(--hover-bg-color);\n",
       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "    fill: var(--button-hover-fill-color);\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart-complete:disabled,\n",
       "  .colab-df-quickchart-complete:disabled:hover {\n",
       "    background-color: var(--disabled-bg-color);\n",
       "    fill: var(--disabled-fill-color);\n",
       "    box-shadow: none;\n",
       "  }\n",
       "\n",
       "  .colab-df-spinner {\n",
       "    border: 2px solid var(--fill-color);\n",
       "    border-color: transparent;\n",
       "    border-bottom-color: var(--fill-color);\n",
       "    animation:\n",
       "      spin 1s steps(1) infinite;\n",
       "  }\n",
       "\n",
       "  @keyframes spin {\n",
       "    0% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "      border-left-color: var(--fill-color);\n",
       "    }\n",
       "    20% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    30% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    40% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    60% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    80% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "    90% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "  }\n",
       "</style>\n",
       "\n",
       "      <script>\n",
       "        async function quickchart(key) {\n",
       "          const quickchartButtonEl =\n",
       "            document.querySelector('#' + key + ' button');\n",
       "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
       "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
       "          try {\n",
       "            const charts = await google.colab.kernel.invokeFunction(\n",
       "                'suggestCharts', [key], {});\n",
       "          } catch (error) {\n",
       "            console.error('Error during call to suggestCharts:', error);\n",
       "          }\n",
       "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
       "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
       "        }\n",
       "        (() => {\n",
       "          let quickchartButtonEl =\n",
       "            document.querySelector('#df-c1ba6420-8195-4d84-b330-88df6a18027c button');\n",
       "          quickchartButtonEl.style.display =\n",
       "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "        })();\n",
       "      </script>\n",
       "    </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   split  fire (1)  no_fire (0)  total  % fire  % no_fire\n",
       "0  train     24792         4745  29537   83.94      16.06\n",
       "1    val      3345          754   4099   81.61      18.39"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from collections import Counter\n",
    "\n",
    "train_targets = Counter(raw_data_target[\"train\"][\"target\"])\n",
    "val_targets = Counter(raw_data_target[\"val\"][\"target\"])\n",
    "\n",
    "train_total = train_targets[0] + train_targets[1]\n",
    "val_total   = val_targets[0] + val_targets[1]\n",
    "\n",
    "pd.DataFrame({\n",
    "    \"split\": [\"train\", \"val\"],\n",
    "    \"fire (1)\": [train_targets[1], val_targets[1]],\n",
    "    \"no_fire (0)\": [train_targets[0], val_targets[0]],\n",
    "    \"total\": [train_total, val_total],\n",
    "    \"% fire\": [\n",
    "        round(train_targets[1] / train_total * 100, 2),\n",
    "        round(val_targets[1] / val_total * 100, 2),\n",
    "    ],\n",
    "    \"% no_fire\": [\n",
    "        round(train_targets[0] / train_total * 100, 2),\n",
    "        round(val_targets[0] / val_total * 100, 2),\n",
    "    ]\n",
    "})\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "D41DpF7wSeoZ"
   },
   "source": [
    "dataset très déséquilibré.  \n",
    "risque de de prédire 'fire' plus souvent --> accuracy trompeuse, fort taux de faux positifs.\n",
    "\n",
    "utiliser class weights dans la fonction de perte (CrossEntropy)  \n",
    "surveiller d’autres métriques que accuracy  \n",
    "analyser les performances sur la classe NO_FIRE  \n",
    "analyser les faux positifs / faux négatifs  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "g5qmMg3yOmyt"
   },
   "source": [
    "## 4. les transformations d’images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 5161,
     "status": "ok",
     "timestamp": 1763118932780,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "giy6NefGXu-a",
    "outputId": "63afc29d-f4ee-44f8-d6e8-91b7c11708d8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "efficientnet_b0  →  (3, 224, 224)\n",
      "efficientnet_b1  →  (3, 240, 240)\n",
      "efficientnet_b2  →  (3, 256, 256)\n",
      "efficientnet_b3  →  (3, 288, 288)\n",
      "efficientnet_b4  →  (3, 320, 320)\n",
      "efficientnet_b5  →  (3, 448, 448)\n",
      "efficientnet_b6  →  (3, 528, 528)\n",
      "efficientnet_b7  →  (3, 600, 600)\n"
     ]
    }
   ],
   "source": [
    "import timm\n",
    "\n",
    "for m in [\"efficientnet_b0\", \"efficientnet_b1\", \"efficientnet_b2\", \"efficientnet_b3\", \"efficientnet_b4\", \"efficientnet_b5\", \"efficientnet_b6\", \"efficientnet_b7\"]:\n",
    "    model = timm.create_model(m, pretrained=False)\n",
    "    print(m, \" → \", model.default_cfg[\"input_size\"])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "I6fLkgT4bc0b"
   },
   "source": [
    "modèles pas pré-entrainés :  \n",
    "efficientnet_b6  →  (3, 528, 528)  \n",
    "efficientnet_b7  →  (3, 600, 600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "uzWVodWCUwHu"
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 1) Import des librairies nécessaires pour les transformations\n",
    "# -----------------------------------------------------------\n",
    "from torchvision import transforms                               # contient les outils de prétraitement d'images pour PyTorch\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 2) Définition des hyperparamètres de base liés aux images\n",
    "# -----------------------------------------------------------\n",
    "IMAGE_SIZE = 224                                                 # taille d'entrée pour EfficientNet (224 x 224 pixels)\n",
    "\n",
    "# Moyennes des canaux RGB pour ImageNet (ordre : R, G, B)\n",
    "IMAGENET_MEAN = [0.485, 0.456, 0.406]                            # utilisé pour normaliser les images comme lors du pré-entraînement\n",
    "\n",
    "# Écarts-types des canaux RGB pour ImageNet\n",
    "IMAGENET_STD = [0.229, 0.224, 0.225]                             # utilisé pour ramener les valeurs de pixels à une échelle adaptée au modèle\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 3) Transformations pour le TRAIN (avec légère augmentation)\n",
    "# -----------------------------------------------------------\n",
    "transform_train = transforms.Compose([                           # Compose permet de chaîner plusieurs transformations\n",
    "\n",
    "    transforms.Resize((IMAGE_SIZE, IMAGE_SIZE)),                 # redimensionne l'image en 224x224 pixels (sans crop compliqué)\n",
    "\n",
    "    transforms.RandomHorizontalFlip(p=0.5),                      # retourne l'image horizontalement avec une probabilité de 50% (data augmentation simple)\n",
    "\n",
    "    transforms.ColorJitter(\n",
    "        brightness=0.2,\n",
    "        contrast=0.2,\n",
    "        saturation=0.1\n",
    "    ),\n",
    "\n",
    "    transforms.ToTensor(),                                       # convertit l'image PIL (0-255) en tenseur PyTorch (0.0-1.0)\n",
    "\n",
    "    transforms.Normalize(mean=IMAGENET_MEAN, std=IMAGENET_STD),  # normalise chaque canal RGB avec les stats d'ImageNet\n",
    "])                                                               # fin de la définition de la pipeline transform_train\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 4) Transformations pour la VAL (sans augmentation)\n",
    "# -----------------------------------------------------------\n",
    "transform_val = transforms.Compose([                             # Compose = pipeline de transformations pour la validation\n",
    "\n",
    "    transforms.Resize((IMAGE_SIZE, IMAGE_SIZE)),                 # redimensionne l'image en 224x224 pixels, comme pour le train\n",
    "\n",
    "    transforms.ToTensor(),                                       # convertit l'image PIL en tenseur (format PyTorch)\n",
    "\n",
    "    transforms.Normalize(mean=IMAGENET_MEAN, std=IMAGENET_STD),  # applique la même normalisation que pour le train\n",
    "])                                                               # fin de la définition de la pipeline transform_val\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "sLp-t_3mB8bL"
   },
   "source": [
    "## 5. DataLoader PyTorch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "7e6pFxERB-vP"
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 1) Raccourcis pour les splits HuggingFace\n",
    "# -----------------------------------------------------------\n",
    "\n",
    "from datasets import Image\n",
    "\n",
    "# Remet le dataset dans un format standard\n",
    "raw_data_target.reset_format()                          # enlève d'éventuels set_format précédents\n",
    "\n",
    "# S'assure que la colonne \"image\" est bien du type Image (PIL)\n",
    "raw_data_target = raw_data_target.cast_column(\"image\", Image())\n",
    "\n",
    "\n",
    "hf_train = raw_data_target[\"train\"]   # split d'entraînement\n",
    "hf_val   = raw_data_target[\"val\"]     # split de validation\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "E1nb246hkGD2"
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 2) Fonction de transform pour le TRAIN (version batch)\n",
    "# -----------------------------------------------------------\n",
    "def apply_train_transform(batch):\n",
    "    \"\"\"\n",
    "    batch : dict avec des LISTES ('image', 'target', etc.)\n",
    "    On applique transform_train à CHAQUE image de batch[\"image\"].\n",
    "    \"\"\"\n",
    "    batch = batch.copy()  # copie superficielle du dict\n",
    "    batch[\"image\"] = [transform_train(img) for img in batch[\"image\"]]  # liste de tensors\n",
    "    return batch\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 3) Fonction de transform pour la VAL (version batch)\n",
    "# -----------------------------------------------------------\n",
    "def apply_val_transform(batch):\n",
    "    \"\"\"\n",
    "    batch : dict avec des LISTES ('image', 'target', etc.)\n",
    "    On applique transform_val à CHAQUE image de batch[\"image\"].\n",
    "    \"\"\"\n",
    "    batch = batch.copy()\n",
    "    batch[\"image\"] = [transform_val(img) for img in batch[\"image\"]]\n",
    "    return batch\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 4) Appliquer ces transforms aux splits HuggingFace\n",
    "# -----------------------------------------------------------\n",
    "hf_train.set_transform(apply_train_transform)\n",
    "hf_val.set_transform(apply_val_transform)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 12,
     "status": "ok",
     "timestamp": 1763118932848,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "i45s5Qsh1E73",
    "outputId": "49e02eb5-d437-43ee-fd29-bae6c117954a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GPU disponible : False\n",
      "Nom du GPU : CPU uniquement\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "\n",
    "print(\"GPU disponible :\", torch.cuda.is_available())\n",
    "print(\"Nom du GPU :\", torch.cuda.get_device_name(0) if torch.cuda.is_available() else \"CPU uniquement\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "W6FGS5m0foGZ"
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 5) Création des DataLoaders pour itérer sur les données par batch\n",
    "# -----------------------------------------------------------\n",
    "\n",
    "from torch.utils.data import DataLoader\n",
    "import torch\n",
    "\n",
    "BATCH_SIZE = 32\n",
    "\n",
    "train_loader = DataLoader(\n",
    "    hf_train,                     # directement le split HuggingFace\n",
    "    batch_size=BATCH_SIZE,\n",
    "    shuffle=True,                 # on mélange pour l'entraînement\n",
    "    num_workers=0,                # travailler plusieurs batch en même temps\n",
    "    pin_memory=True if torch.cuda.is_available() else False\n",
    ")\n",
    "\n",
    "val_loader = DataLoader(\n",
    "    hf_val,\n",
    "    batch_size=BATCH_SIZE,\n",
    "    shuffle=False,                # pas besoin de shuffle pour la validation\n",
    "    num_workers=0,\n",
    "    pin_memory=True if torch.cuda.is_available() else False\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 558,
     "status": "ok",
     "timestamp": 1763118933418,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "yGU_oC6ysv9R",
    "outputId": "d04bddf9-180d-4ec2-ad8b-b31e7de168cd"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Type images : <class 'torch.Tensor'>\n",
      "Shape images : torch.Size([32, 3, 224, 224])\n",
      "Type labels : <class 'torch.Tensor'>\n",
      "Shape labels : torch.Size([32])\n",
      "Quelques labels : tensor([1, 1, 1, 0, 1, 1, 1, 1, 1, 0])\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 6) Test : récupérer un batch et regarder les shapes\n",
    "# -----------------------------------------------------------\n",
    "\n",
    "batch = next(iter(train_loader))          # on prend le premier batch du train_loader\n",
    "\n",
    "images = batch[\"image\"]                   # batch d'images (tensors)\n",
    "labels = batch[\"target\"]                  # batch de labels (0/1)\n",
    "\n",
    "print(\"Type images :\", type(images))      # torch.Tensor\n",
    "print(\"Shape images :\", images.shape)     # [batch_size, 3, 224, 224]\n",
    "\n",
    "print(\"Type labels :\", type(labels))      # torch.Tensor ou list -> selon version, mais DataLoader les colle bien\n",
    "print(\"Shape labels :\", labels.shape)     # [batch_size] si tensor\n",
    "\n",
    "print(\"Quelques labels :\", labels[:10])   # affichage des 10 premiers labels\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "sP4T761KB-87"
   },
   "source": [
    "## 6. Model EfficientNet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 411,
     "status": "ok",
     "timestamp": 1763118933826,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "yd-r7RqNO43L",
    "outputId": "c9773d3a-a9fa-4569-db85-0a4184aeea85"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "EfficientNet(\n",
      "  (conv_stem): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
      "  (bn1): BatchNormAct2d(\n",
      "    32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "    (drop): Identity()\n",
      "    (act): SiLU(inplace=True)\n",
      "  )\n",
      "  (blocks): Sequential(\n",
      "    (0): Sequential(\n",
      "      (0): DepthwiseSeparableConv(\n",
      "        (conv_dw): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(32, 8, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(8, 32, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pw): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "    )\n",
      "    (1): Sequential(\n",
      "      (0): InvertedResidual(\n",
      "        (conv_pw): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(96, 4, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(4, 96, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (1): InvertedResidual(\n",
      "        (conv_pw): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "    )\n",
      "    (2): Sequential(\n",
      "      (0): InvertedResidual(\n",
      "        (conv_pw): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(144, 144, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=144, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          40, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (1): InvertedResidual(\n",
      "        (conv_pw): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=240, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          40, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "    )\n",
      "    (3): Sequential(\n",
      "      (0): InvertedResidual(\n",
      "        (conv_pw): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(240, 240, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=240, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(240, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (1): InvertedResidual(\n",
      "        (conv_pw): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=480, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (2): InvertedResidual(\n",
      "        (conv_pw): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=480, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "    )\n",
      "    (4): Sequential(\n",
      "      (0): InvertedResidual(\n",
      "        (conv_pw): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(480, 480, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=480, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(480, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (1): InvertedResidual(\n",
      "        (conv_pw): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=672, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (2): InvertedResidual(\n",
      "        (conv_pw): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=672, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "    )\n",
      "    (5): Sequential(\n",
      "      (0): InvertedResidual(\n",
      "        (conv_pw): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(672, 672, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=672, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (1): InvertedResidual(\n",
      "        (conv_pw): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (2): InvertedResidual(\n",
      "        (conv_pw): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "      (3): InvertedResidual(\n",
      "        (conv_pw): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "    )\n",
      "    (6): Sequential(\n",
      "      (0): InvertedResidual(\n",
      "        (conv_pw): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn1): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (conv_dw): Conv2d(1152, 1152, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=1152, bias=False)\n",
      "        (bn2): BatchNormAct2d(\n",
      "          1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): SiLU(inplace=True)\n",
      "        )\n",
      "        (aa): Identity()\n",
      "        (se): SqueezeExcite(\n",
      "          (conv_reduce): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (act1): SiLU(inplace=True)\n",
      "          (conv_expand): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))\n",
      "          (gate): Sigmoid()\n",
      "        )\n",
      "        (conv_pwl): Conv2d(1152, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "        (bn3): BatchNormAct2d(\n",
      "          320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "          (drop): Identity()\n",
      "          (act): Identity()\n",
      "        )\n",
      "        (drop_path): Identity()\n",
      "      )\n",
      "    )\n",
      "  )\n",
      "  (conv_head): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
      "  (bn2): BatchNormAct2d(\n",
      "    1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True\n",
      "    (drop): Identity()\n",
      "    (act): SiLU(inplace=True)\n",
      "  )\n",
      "  (global_pool): SelectAdaptivePool2d(pool_type=avg, flatten=Flatten(start_dim=1, end_dim=-1))\n",
      "  (classifier): Linear(in_features=1280, out_features=2, bias=True)\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 1) Import du modèle EfficientNet-B0 depuis timm\n",
    "# -----------------------------------------------------------\n",
    "import timm\n",
    "import torch.nn as nn\n",
    "\n",
    "# Charger EfficientNet-B0 pré-entraîné sur ImageNet\n",
    "model = timm.create_model(\"efficientnet_b0\", pretrained=True)\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 2) On remplace la dernière couche par une couche à 2 sorties\n",
    "# -----------------------------------------------------------\n",
    "\n",
    "# La tête originale est dans model.classifier\n",
    "in_features = model.classifier.in_features     # taille d'entrée de la dernière couche\n",
    "\n",
    "model.classifier = nn.Linear(in_features, 2)   # nouvelle tête pour 2 classes (fire / no_fire)\n",
    "\n",
    "print(model)  # optionnel : pour voir la structure finale\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 12,
     "status": "ok",
     "timestamp": 1763118933855,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "bQ5Rv7ib3cSe",
    "outputId": "8c5206ca-eaa5-461b-bb58-feac036ac79a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GPU disponible : False\n",
      "Nom du GPU : CPU uniquement\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 3) Placer le modèle sur GPU si disponible\n",
    "# -----------------------------------------------------------\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "model = model.to(device)\n",
    "\n",
    "import torch\n",
    "\n",
    "print(\"GPU disponible :\", torch.cuda.is_available())\n",
    "print(\"Nom du GPU :\", torch.cuda.get_device_name(0) if torch.cuda.is_available() else \"CPU uniquement\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 12,
     "status": "ok",
     "timestamp": 1763118933869,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "jxIxMubN3d_G",
    "outputId": "aa9825b4-7313-453d-9300-69dac249b4e6"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Weights: tensor([3.1124, 0.5957])\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "import torch.nn as nn # Ensure nn is imported if not already\n",
    "\n",
    "# Use the counts already calculated in cell ruhjpk7yFyhu\n",
    "n_fire = train_fire\n",
    "n_no_fire = train_no_fire\n",
    "n_total = n_fire + n_no_fire\n",
    "\n",
    "# Poids inverses (classe minoritaire = poids plus grand)\n",
    "w_no_fire = n_total / (2 * n_no_fire)\n",
    "w_fire    = n_total / (2 * n_fire)\n",
    "\n",
    "class_weights = torch.tensor([w_no_fire, w_fire]).to(device)\n",
    "print(\"Weights:\", class_weights)\n",
    "\n",
    "\n",
    "loss_fn = nn.CrossEntropyLoss(weight=class_weights)\n",
    "\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 5) Optimizer (Adam est très bien pour débuter)\n",
    "# -----------------------------------------------------------\n",
    "optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 5,
     "status": "ok",
     "timestamp": 1763118933875,
     "user": {
      "displayName": "Nina BIAO",
      "userId": "01787547558561747396"
     },
     "user_tz": -60
    },
    "id": "IAYTX3s43g-b",
    "outputId": "acf55bb3-52c4-44f2-b0cc-6c90aad3c7ba"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Modèle prêt sur : cpu\n"
     ]
    }
   ],
   "source": [
    "print(\"Modèle prêt sur :\", device)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "7ke6hckv7_OI"
   },
   "source": [
    "## 7. EfficientNet - Feature Extraction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "C4UB2A9r8ADw"
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 1) Geler toutes les couches du modèle (feature extraction)\n",
    "# -----------------------------------------------------------\n",
    "for param in model.parameters():                  # on parcourt tous les paramètres du modèle\n",
    "    param.requires_grad = False                   # on bloque leur entraînement (pas de mise à jour des poids)\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 2) Débloquer seulement la dernière couche (la tête de classification)\n",
    "# -----------------------------------------------------------\n",
    "for param in model.classifier.parameters():       # on parcourt les paramètres de la dernière couche (nn.Linear)\n",
    "    param.requires_grad = True                    # on autorise leur entraînement\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 3) Redéfinir l'optimizer pour n'entraîner QUE la tête\n",
    "# -----------------------------------------------------------\n",
    "optimizer = torch.optim.Adam(                     # on choisit l'optimizer Adam\n",
    "    model.classifier.parameters(),                # on lui donne uniquement les paramètres de la tête\n",
    "    lr=1e-4                                       # petit learning rate adapté au transfer learning\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "JUY1UHflB3eN"
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 4) Définir le nombre d'epochs\n",
    "# -----------------------------------------------------------\n",
    "EPOCHS = 3                                                                  # nombre de passages complets sur le dataset d'entraînement\n",
    "\n",
    "# -----------------------------------------------------------\n",
    "# 5) Boucle principale d'entraînement\n",
    "# -----------------------------------------------------------\n",
    "for epoch in range(EPOCHS):                                                 # boucle sur chaque epoch\n",
    "    # ------------------ PARTIE TRAIN -----------------------\n",
    "    model.train()                                                           # on met le modèle en mode entraînement\n",
    "\n",
    "    running_loss = 0.0                                                      # cumul de la loss sur l'epoch\n",
    "    correct = 0                                                             # compteur de prédictions correctes\n",
    "    total = 0                                                               # compteur de labels vus\n",
    "\n",
    "    for batch in train_loader:                                              # on parcourt tous les batches du train_loader\n",
    "        images = batch[\"image\"].to(device)                                  # on récupère les images et on les envoie sur CPU/GPU\n",
    "        labels = batch[\"target\"].to(device)                                 # on récupère les labels (0/1) et on les envoie sur CPU/GPU\n",
    "\n",
    "        optimizer.zero_grad()                                               # on remet les gradients à zéro pour ce batch\n",
    "\n",
    "        outputs = model(images)                                             # le modèle produit des logits (scores bruts pour chaque classe)\n",
    "        loss = loss_fn(outputs, labels)                                     # on calcule la loss entre les prédictions et les vrais labels\n",
    "\n",
    "        loss.backward()                                                     # on calcule les gradients de la loss par rapport aux poids\n",
    "        optimizer.step()                                                    # on met à jour les poids (uniquement ceux de la tête)\n",
    "\n",
    "        running_loss += loss.item() * labels.size(0)                        # on cumule la loss pondérée par le nombre d'éléments du batch\n",
    "\n",
    "        _, preds = torch.max(outputs, dim=1)                                # on récupère la classe prédite (0 ou 1) pour chaque image\n",
    "        correct += (preds == labels).sum().item()                           # on ajoute le nombre de prédictions correctes\n",
    "        total += labels.size(0)                                             # on ajoute le nombre total d'images vues\n",
    "\n",
    "    train_loss = running_loss / total                                       # loss moyenne sur tout le train\n",
    "    train_acc = correct / total                                             # accuracy moyenne sur tout le train\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "T6qwphsJC48P"
   },
   "outputs": [],
   "source": [
    "\n",
    "    # ------------------ AFFICHAGE DES STATISTIQUES ---------\n",
    "    print(f\"Epoch {epoch+1}/{EPOCHS}\")                                      # affichage du numéro d'epoch\n",
    "    print(f\"  Train    - Loss: {train_loss:.4f}  | Acc: {train_acc:.4f}\")   # stats train\n",
    "    print(\"-\" * 60)                                                         # ligne de séparation visuelle\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "tkUxfYTHCru7"
   },
   "outputs": [],
   "source": [
    "\n",
    "    # ------------------ PARTIE VALIDATION ------------------\n",
    "    model.eval()                                                            # on met le modèle en mode évaluation (pas de dropout, etc.)\n",
    "\n",
    "    val_running_loss = 0.0                                                  # cumul de la loss sur la validation\n",
    "    val_correct = 0                                                         # compteur de prédictions correctes\n",
    "    val_total = 0                                                           # compteur de labels vus\n",
    "\n",
    "    # variables pour calculer le recall de la classe FIRE (label 1)\n",
    "    fire_true = 0                                                           # nombre de vrais exemples FIRE (label = 1)\n",
    "    fire_true_positive = 0                                                  # parmi eux, combien correctement prédits FIRE ?\n",
    "\n",
    "    # variable pour calculer la précision de la classe FIRE\n",
    "    fire_pred_positive = 0                                                  # nombre total de prédictions FIRE (preds == 1)\n",
    "\n",
    "    with torch.no_grad():                                                   # on désactive le calcul des gradients (plus rapide, moins de mémoire)\n",
    "        for batch in val_loader:                                            # on parcourt tous les batches de validation\n",
    "            images = batch[\"image\"].to(device)                              # images → CPU/GPU\n",
    "            labels = batch[\"target\"].to(device)                             # labels (0/1) → CPU/GPU\n",
    "\n",
    "            outputs = model(images)                                         # logits du modèle\n",
    "            loss = loss_fn(outputs, labels)                                 # loss de validation pour ce batch\n",
    "\n",
    "            val_running_loss += loss.item() * labels.size(0)                # cumul de la loss\n",
    "\n",
    "            _, preds = torch.max(outputs, dim=1)                            # prédictions (0 ou 1)\n",
    "            val_correct += (preds == labels).sum().item()                   # on ajoute les bonnes prédictions\n",
    "            val_total += labels.size(0)                                     # on ajoute le nombre d'images vues\n",
    "\n",
    "            # --- calcul du recall pour la classe FIRE (1) ---\n",
    "            fire_mask = (labels == 1)                                       # masque booléen des exemples FIRE\n",
    "            fire_true += fire_mask.sum().item()                             # nombre total d'exemples FIRE dans ce batch\n",
    "\n",
    "            fire_true_positive += ((preds == 1) & fire_mask).sum().item()   # parmi eux, ceux bien prédits FIRE\n",
    "\n",
    "            # --- calcul de la précision pour FIRE (1) ---\n",
    "            fire_pred_positive += (preds == 1).sum().item()                 # toutes les prédictions FIRE (TP + FP)\n",
    "\n",
    "    val_loss = val_running_loss / val_total                                 # loss moyenne sur la validation\n",
    "    val_acc = val_correct / val_total                                       # accuracy moyenne sur la validation\n",
    "\n",
    "\n",
    "    # Recall FIRE\n",
    "    if fire_true > 0:                                                       # on vérifie qu'il y a bien des exemples FIRE\n",
    "        val_recall_fire = fire_true_positive / fire_true                    # recall = TP / (TP + FN) pour la classe FIRE\n",
    "    else:\n",
    "        val_recall_fire = 0.0                                               # cas extrême (peu probable) où il n'y aurait aucun FIRE en validation\n",
    "\n",
    "    # Precision FIRE\n",
    "    if fire_pred_positive > 0:\n",
    "        val_precision_fire = fire_true_positive / fire_pred_positive\n",
    "    else:\n",
    "        val_precision_fire = 0.0\n",
    "\n",
    "    # F1-score FIRE\n",
    "    if val_precision_fire + val_recall_fire > 0:\n",
    "        val_f1_fire = 2 * (val_precision_fire * val_recall_fire) / (val_precision_fire + val_recall_fire)\n",
    "    else:\n",
    "        val_f1_fire = 0.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "hTV9fLwIC1By"
   },
   "outputs": [],
   "source": [
    "\n",
    "    # ------------------ AFFICHAGE DES STATISTIQUES ---------\n",
    "    print(f\"Epoch {epoch+1}/{EPOCHS}\")\n",
    "    print(f\"  Train    - Loss: {train_loss:.4f}  | Acc: {train_acc:.4f}\")\n",
    "    print(f\"  Val      - Loss: {val_loss:.4f}    | Acc: {val_acc:.4f}  \"\n",
    "          f\"| Recall FIRE: {val_recall_fire:.4f}  | Precision FIRE: {val_precision_fire:.4f}  | F1 FIRE: {val_f1_fire:.4f}\")\n",
    "    print(\"-\" * 60)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "-ZWr_fHS6BPA"
   },
   "source": [
    "## 8. Évaluation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "4D9ZrdA06i0q"
   },
   "source": [
    "### Récupérer toutes les prédictions sur la validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "T4DOSgZ66D-3"
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------------------\n",
    "# 6A) Récupérer toutes les prédictions sur la validation\n",
    "# -----------------------------------------------------------\n",
    "import torch\n",
    "\n",
    "model.eval()                              # on met le modèle en mode évaluation\n",
    "\n",
    "y_true = []                               # liste des vrais labels (0/1)\n",
    "y_pred = []                               # liste des labels prédits (0/1)\n",
    "y_prob = []                               # liste des probabilités prédites pour FIRE (classe 1)\n",
    "val_images = []                           # pour stocker les images correspondantes (tensors)\n",
    "\n",
    "with torch.no_grad():                     # pas de calcul de gradients pendant l'évaluation\n",
    "    for batch in val_loader:              # on parcourt tous les batches de validation\n",
    "\n",
    "        images_cpu = batch[\"image\"]       # images sur CPU (tensors déjà transformés)\n",
    "        labels = batch[\"target\"]          # vrais labels (0/1) sur CPU\n",
    "\n",
    "        images = images_cpu.to(device)    # on envoie une copie des images sur le device (CPU/GPU)\n",
    "        labels = labels.to(device)        # on envoie les labels sur le device\n",
    "\n",
    "        outputs = model(images)           # logits du modèle : taille [batch_size, 2]\n",
    "\n",
    "        # Probabilité de la classe FIRE (indice 1)\n",
    "        probs_fire = torch.softmax(outputs, dim=1)[:, 1]  # on garde la colonne de la classe 1\n",
    "\n",
    "        # Prédiction finale = argmax des logits (0 ou 1)\n",
    "        preds = torch.argmax(outputs, dim=1)\n",
    "\n",
    "        # On repasse tout sur CPU et on convertit en listes Python\n",
    "        y_true.extend(labels.cpu().tolist())\n",
    "        y_pred.extend(preds.cpu().tolist())\n",
    "        y_prob.extend(probs_fire.cpu().tolist())\n",
    "\n",
    "        # On garde aussi les images du batch sur CPU pour analyse ultérieure (FP/FN)\n",
    "        val_images.extend(images_cpu)     # images_cpu est déjà sur CPU\n",
    "\n",
    "# Vérification rapide des tailles\n",
    "print(\"Nombre d'exemples en validation :\", len(y_true))\n",
    "print(\"Même taille pour y_pred :\", len(y_pred))\n",
    "print(\"Même taille pour y_prob :\", len(y_prob))\n",
    "print(\"Nombre d'images stockées :\", len(val_images))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gRtboJwL6mnn"
   },
   "source": [
    "### matrice de confusion"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "sAsH6vHe6obv"
   },
   "source": [
    "### classification report (precision, recall, F1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ikcV8plk6pHs"
   },
   "source": [
    "### quelques exemples"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "kchF0c646p04"
   },
   "source": [
    "### tracer les courbes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MMbEILvkO5gk"
   },
   "source": [
    "## 8. EfficientNet - Fine-tuning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "MnqpquK5PSgj"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "QYPMr0N7B6Mm"
   },
   "source": [
    "## 9. Evaluation Fine-tuining"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "H5aWYKsPCGyZ"
   },
   "source": [
    "## 10. Tests"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "amN1Odv1CMUA"
   },
   "source": [
    "## 11. Export du modèle"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wR2xNPOoCfEh"
   },
   "source": [
    "### Sauvegarder les poids du modèle dans Colab"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "PVgmlaE3Cjbd"
   },
   "outputs": [],
   "source": [
    "model_path = \"/content/efficientnet_fire.pt\"\n",
    "torch.save(model.state_dict(), model_path)\n",
    "\n",
    "print(\"Modèle sauvegardé à :\", model_path)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_bfuy5RmC5Sm"
   },
   "source": [
    "### Copier le modèle dans le Google Drive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "kEZ73x9yC-kd"
   },
   "outputs": [],
   "source": [
    "from google.colab import drive\n",
    "drive.mount('/content/drive')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "RdIKaL1wDBV6"
   },
   "outputs": [],
   "source": [
    "drive_model_path = \"/content/drive/MyDrive/Colab_Notebooks/Fire_Detection/efficientnet_fire.pt\"\n",
    "\n",
    "!cp /content/efficientnet_fire.pt $drive_model_path\n",
    "\n",
    "print(\"Modèle copié dans ton Drive :\", drive_model_path)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "rvohu05UPSO-"
   },
   "source": [
    "## 12. Script de l’inférence"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "AfLPbkXwPjFB"
   },
   "source": [
    "inference.py"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "cDAjuq24PYbk"
   },
   "source": [
    "## 13. Intégration dans un petit dashboard (Streamlit)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "VmHwi0imPYDS"
   },
   "outputs": [],
   "source": [
    "import streamlit as st\n",
    "st.write(\"This is my new app\")"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "authorship_tag": "ABX9TyNPftGwwy7OzEsdiABHODIV",
   "gpuType": "T4",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "name": "python3"
  },
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}