Lung_Tumor_Detect_TCX.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yPX-_7RovS6T",
        "outputId": "28855118-3947-4f5c-d49e-e1fa02459046"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "#imports\n",
        "\n",
        "import tensorflow as tf\n",
        "import os\n",
        "import cv2\n",
        "import random\n",
        "from PIL import Image\n",
        "import shutil\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "from tensorflow.keras.applications.mobilenet_v2 import preprocess_input\n",
        "from keras.utils import to_categorical\n",
        "from sklearn.utils import shuffle\n",
        "from tensorflow.keras.applications import VGG16\n",
        "from keras.src.metrics.confusion_metrics import activations\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Conv2D,Dense,MaxPooling2D,Flatten,BatchNormalization,Dropout,Activation\n",
        "from tensorflow.keras.models import load_model\n",
        "from google.colab import drive\n",
        "drive.mount(\"/content/drive\", force_remount=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "u4q2i51uLERs",
        "outputId": "83fc5779-2479-4b02-f1f6-d8dadd5d2dcc"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['valid', 'train', 'test']\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['squamous.cell.carcinoma', 'normal', 'large.cell.carcinoma', 'adenocarcinoma']"
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ],
      "source": [
        "data_dir = '/content/drive/MyDrive/Data-Copy'\n",
        "train_folder = os.path.join(data_dir, 'train')\n",
        "valid_folder = os.path.join(data_dir, 'valid')\n",
        "test_folder = os.path.join(data_dir, 'test')\n",
        "print(os.listdir(data_dir))\n",
        "Cclasses = os.listdir(test_folder)\n",
        "Cclasses"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Data control"
      ],
      "metadata": {
        "id": "vnt0jnZOOs8_"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ocg5e1_VF_4O"
      },
      "outputs": [],
      "source": [
        "\n",
        "#deleting corrupted files\n",
        "\n",
        "def filter_images(folder_path):\n",
        "    for root, dirs, files in os.walk(folder_path):\n",
        "        for filename in files:\n",
        "            file_path = os.path.join(root, filename)\n",
        "\n",
        "            if file_path.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.bmp')):\n",
        "                try:\n",
        "\n",
        "                    with Image.open(file_path) as img:\n",
        "                        img.verify()\n",
        "                except OSError:\n",
        "\n",
        "                    print(f\"Removing: {file_path}\")\n",
        "                    os.remove(file_path)\n",
        "            else:\n",
        "\n",
        "                print(f\"Removing: {file_path} - Unsupported file type\")\n",
        "                os.remove(file_path)\n",
        "\n",
        "filter_images(test_folder)\n",
        "filter_images(train_folder)\n",
        "filter_images(valid_folder)\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "#  oversample a class\n",
        "def oversample_class(class_folder, target_count):\n",
        "    files = os.listdir(class_folder)\n",
        "    current_count = len(files)\n",
        "\n",
        "    oversample_count = target_count - current_count\n",
        "    if oversample_count > 0:\n",
        "        oversampled_files = random.choices(files, k=oversample_count)\n",
        "        for file in oversampled_files:\n",
        "            source_path = os.path.join(class_folder, file)\n",
        "            destination_path = os.path.join(class_folder, f\"copy_{file}\")\n",
        "            shutil.copyfile(source_path, destination_path)\n",
        "\n",
        "# undersample a class\n",
        "def undersample_class(class_folder, target_count):\n",
        "    files = os.listdir(class_folder)\n",
        "    current_count = len(files)\n",
        "\n",
        "    undersample_count = current_count - target_count\n",
        "    if undersample_count > 0:\n",
        "        undersampled_files = random.sample(files, k=undersample_count)\n",
        "        for file in undersampled_files:\n",
        "            file_path = os.path.join(class_folder, file)\n",
        "            os.remove(file_path)\n",
        "\n",
        "target_count = 181\n",
        "\n",
        "for Cclass in os.listdir(train_folder):\n",
        "    class_folder_train = os.path.join(train_folder, Cclass)\n",
        "\n",
        "    # oversampling\n",
        "    oversample_condition = len(os.listdir(class_folder_train)) < target_count\n",
        "    if oversample_condition:\n",
        "        oversample_class(class_folder_train, target_count)\n",
        "\n",
        "    # undersampling\n",
        "    undersample_condition = len(os.listdir(class_folder_train)) > target_count\n",
        "    if undersample_condition:\n",
        "        undersample_class(class_folder_train, target_count)\n"
      ],
      "metadata": {
        "id": "wPSy42sNpx_h"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "G7hU85t7qt6J",
        "outputId": "5d573614-8746-4996-9ebc-edd869a46ebb"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Folder: /content/drive/MyDrive/Data-Copy/test\n",
            "  Class: squamous.cell.carcinoma - Count: 90 - Percentage: 28.57%\n",
            "  Class: normal - Count: 54 - Percentage: 17.14%\n",
            "  Class: large.cell.carcinoma - Count: 51 - Percentage: 16.19%\n",
            "  Class: adenocarcinoma - Count: 120 - Percentage: 38.10%\n",
            "  Total Files: 315\n",
            "\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/squamous.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/squamous.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/large.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/large.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/adenocarcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/adenocarcinoma'\n",
            "Folder: /content/drive/MyDrive/Data-Copy/train\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/squamous.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/squamous.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/squamous.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/squamous.cell.carcinoma'\n",
            "  Class: squamous.cell.carcinoma - Count: 0 - Percentage: 0.00%\n",
            "  Class: normal - Count: 181 - Percentage: 100.00%\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/large.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/large.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/large.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/large.cell.carcinoma'\n",
            "  Class: large.cell.carcinoma - Count: 0 - Percentage: 0.00%\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/adenocarcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/adenocarcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/train/adenocarcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/train/adenocarcinoma'\n",
            "  Class: adenocarcinoma - Count: 0 - Percentage: 0.00%\n",
            "  Total Files: 181\n",
            "\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/squamous.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/squamous.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/large.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/large.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/adenocarcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/adenocarcinoma'\n",
            "Folder: /content/drive/MyDrive/Data-Copy/valid\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/squamous.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/squamous.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/squamous.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/squamous.cell.carcinoma'\n",
            "  Class: squamous.cell.carcinoma - Count: 0 - Percentage: 0.00%\n",
            "  Class: normal - Count: 13 - Percentage: 100.00%\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/large.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/large.cell.carcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/large.cell.carcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/large.cell.carcinoma'\n",
            "  Class: large.cell.carcinoma - Count: 0 - Percentage: 0.00%\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/adenocarcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/adenocarcinoma'\n",
            "Error counting files in /content/drive/MyDrive/Data-Copy/valid/adenocarcinoma: [Errno 2] No such file or directory: '/content/drive/MyDrive/Data-Copy/valid/adenocarcinoma'\n",
            "  Class: adenocarcinoma - Count: 0 - Percentage: 0.00%\n",
            "  Total Files: 13\n",
            "\n"
          ]
        }
      ],
      "source": [
        "\n",
        "\n",
        "\n",
        "# Function to count the number of files in a folder\n",
        "def count_files(folder_path):\n",
        "    try:\n",
        "        with os.scandir(folder_path) as entries:\n",
        "            return sum(1 for entry in entries if entry.is_file() and not entry.name.startswith('.'))\n",
        "    except OSError as e:\n",
        "        print(f\"Error counting files in {folder_path}: {e}\")\n",
        "        return 0\n",
        "\n",
        "# Function to calculate the percentage of files in a folder\n",
        "def calculate_percentage(folder_path, total_files):\n",
        "    folder_files = count_files(folder_path)\n",
        "    return (folder_files / total_files) * 100 if total_files > 0 else 0\n",
        "\n",
        "# Iterate through test, train, and valid folders\n",
        "for folder in [test_folder, train_folder, valid_folder]:\n",
        "    total_files = sum([count_files(os.path.join(folder, class_name)) for class_name in Cclasses])\n",
        "\n",
        "    print(f\"Folder: {folder}\")\n",
        "    for class_name in Cclasses:\n",
        "        class_folder = os.path.join(folder, class_name)\n",
        "        class_count = count_files(class_folder)\n",
        "        class_percentage = calculate_percentage(class_folder, total_files)\n",
        "        print(f\"  Class: {class_name} - Count: {class_count} - Percentage: {class_percentage:.2f}%\")\n",
        "\n",
        "    print(f\"  Total Files: {total_files}\")\n",
        "    print()\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Model"
      ],
      "metadata": {
        "id": "s34GxUnOO7af"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ta1p5Cqi0RVv",
        "outputId": "ebcb28fa-82b0-4fb3-cdb4-8b21f02a5214"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 718 images belonging to 4 classes.\n",
            "Found 72 images belonging to 4 classes.\n",
            "Found 315 images belonging to 4 classes.\n"
          ]
        }
      ],
      "source": [
        "\n",
        "#buiding generators\n",
        "basic_gen = ImageDataGenerator(\n",
        "    preprocessing_function = preprocess_input,\n",
        "    dtype = 'float32'\n",
        ")\n",
        "train_gen = ImageDataGenerator(\n",
        "    preprocessing_function = preprocess_input,\n",
        "    rotation_range = 20,\n",
        "    width_shift_range = 0.3,\n",
        "    height_shift_range = 0.3,\n",
        "    zoom_range = 0.2,\n",
        "    horizontal_flip = True,\n",
        "    vertical_flip = True,\n",
        "    dtype = 'float32'\n",
        ")\n",
        "#data gen\n",
        "train_data = train_gen.flow_from_directory(\n",
        "    train_folder,\n",
        "    target_size = (224,224),\n",
        "    batch_size = 16,\n",
        "    class_mode = 'categorical'\n",
        ")\n",
        "\n",
        "valid_data = basic_gen.flow_from_directory(\n",
        "    valid_folder,\n",
        "    target_size = (224,224),\n",
        "    batch_size = 16,\n",
        "    class_mode = 'categorical'\n",
        ")\n",
        "\n",
        "test_data = basic_gen.flow_from_directory(\n",
        "    test_folder,\n",
        "    target_size = (224,224),\n",
        "    batch_size = 16,\n",
        "    class_mode = 'categorical',\n",
        "    shuffle = True\n",
        ")\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dEHtL777QMMI",
        "outputId": "0739fca3-3cd8-4844-c8ea-0d5c3cf7a806"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "58889256/58889256 [==============================] - 1s 0us/step\n",
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " vgg16 (Functional)          (None, 7, 7, 512)         14714688  \n",
            "                                                                 \n",
            " batch_normalization (Batch  (None, 7, 7, 512)         2048      \n",
            " Normalization)                                                  \n",
            "                                                                 \n",
            " max_pooling2d (MaxPooling2  (None, 3, 3, 512)         0         \n",
            " D)                                                              \n",
            "                                                                 \n",
            " flatten (Flatten)           (None, 4608)              0         \n",
            "                                                                 \n",
            " dense (Dense)               (None, 1024)              4719616   \n",
            "                                                                 \n",
            " dropout (Dropout)           (None, 1024)              0         \n",
            "                                                                 \n",
            " dense_1 (Dense)             (None, 512)               524800    \n",
            "                                                                 \n",
            " dropout_1 (Dropout)         (None, 512)               0         \n",
            "                                                                 \n",
            " dense_2 (Dense)             (None, 256)               131328    \n",
            "                                                                 \n",
            " dense_3 (Dense)             (None, 4)                 1028      \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 20093508 (76.65 MB)\n",
            "Trainable params: 5377796 (20.51 MB)\n",
            "Non-trainable params: 14715712 (56.14 MB)\n",
            "_________________________________________________________________\n"
          ]
        }
      ],
      "source": [
        "#building model\n",
        "\n",
        "input_shape=(224,224,3)\n",
        "\n",
        "base_model = VGG16(\n",
        "    include_top = False,\n",
        "    weights=\"imagenet\",\n",
        "    input_shape = input_shape\n",
        ")\n",
        "\n",
        "#freezing layers to use the model as feature extractor\n",
        "for layer in base_model.layers:\n",
        "    layer.trainable = False\n",
        "\n",
        "\n",
        "model = Sequential()\n",
        "model.add(base_model)\n",
        "model.add(BatchNormalization())\n",
        "model.add(MaxPooling2D((2,2)))\n",
        "model.add(Flatten())\n",
        "model.add(Dense(1024,activation = 'relu'))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(Dense(512,activation = 'relu'))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(Dense(256,activation = 'relu'))\n",
        "model.add(Dense(4,activation = 'softmax'))\n",
        "model.summary()\n",
        "\n",
        "# Compile the model\n",
        "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 391
        },
        "id": "I0BMxCxF6Cqz",
        "outputId": "37cc4bd1-c4ea-453b-b3b3-72c034324dfc"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "45/45 [==============================] - ETA: 0s - loss: 0.3112 - accuracy: 0.8900"
          ]
        },
        {
          "output_type": "error",
          "ename": "KeyboardInterrupt",
          "evalue": "",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-37-bf967385a9ab>\u001b[0m in \u001b[0;36m<cell line: 11>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      9\u001b[0m     \u001b[0mreduce_lr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     10\u001b[0m ]\n\u001b[0;32m---> 11\u001b[0;31m \u001b[0mresults\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalid_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m100\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     63\u001b[0m         \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     64\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 65\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     66\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     67\u001b[0m             \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m   1854\u001b[0m                             \u001b[0mpss_evaluation_shards\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_pss_evaluation_shards\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1855\u001b[0m                         )\n\u001b[0;32m-> 1856\u001b[0;31m                     val_logs = self.evaluate(\n\u001b[0m\u001b[1;32m   1857\u001b[0m                         \u001b[0mx\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mval_x\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1858\u001b[0m                         \u001b[0my\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mval_y\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     63\u001b[0m         \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     64\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 65\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     66\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     67\u001b[0m             \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py\u001b[0m in \u001b[0;36mevaluate\u001b[0;34m(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, max_queue_size, workers, use_multiprocessing, return_dict, **kwargs)\u001b[0m\n\u001b[1;32m   2294\u001b[0m                         ):\n\u001b[1;32m   2295\u001b[0m                             \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_test_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2296\u001b[0;31m                             logs = test_function_runner.run_step(\n\u001b[0m\u001b[1;32m   2297\u001b[0m                                 \u001b[0mdataset_or_iterator\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2298\u001b[0m                                 \u001b[0mdata_handler\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py\u001b[0m in \u001b[0;36mrun_step\u001b[0;34m(self, dataset_or_iterator, data_handler, step, unused_shards)\u001b[0m\n\u001b[1;32m   4106\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4107\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mrun_step\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdataset_or_iterator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstep\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0munused_shards\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4108\u001b[0;31m         \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset_or_iterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   4109\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4110\u001b[0m             \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    148\u001b[0m     \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    149\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 150\u001b[0;31m       \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    151\u001b[0m     \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    152\u001b[0m       \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    830\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    831\u001b[0m       \u001b[0;32mwith\u001b[0m \u001b[0mOptionalXlaContext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_jit_compile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 832\u001b[0;31m         \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    833\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    834\u001b[0m       \u001b[0mnew_tracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    875\u001b[0m       \u001b[0;31m# In this case we have not created variables on the first call. So we can\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    876\u001b[0m       \u001b[0;31m# run the first trace but we should fail if variables are created.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 877\u001b[0;31m       results = tracing_compilation.call_function(\n\u001b[0m\u001b[1;32m    878\u001b[0m           \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_variable_creation_config\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    879\u001b[0m       )\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/polymorphic_function/tracing_compilation.py\u001b[0m in \u001b[0;36mcall_function\u001b[0;34m(args, kwargs, tracing_options)\u001b[0m\n\u001b[1;32m    137\u001b[0m   \u001b[0mbound_args\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunction\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfunction_type\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbind\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    138\u001b[0m   \u001b[0mflat_inputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunction\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfunction_type\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munpack_inputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbound_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 139\u001b[0;31m   return function._call_flat(  # pylint: disable=protected-access\n\u001b[0m\u001b[1;32m    140\u001b[0m       \u001b[0mflat_inputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcaptured_inputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfunction\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcaptured_inputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    141\u001b[0m   )\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/polymorphic_function/concrete_function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[0;34m(self, tensor_inputs, captured_inputs)\u001b[0m\n\u001b[1;32m   1321\u001b[0m         and executing_eagerly):\n\u001b[1;32m   1322\u001b[0m       \u001b[0;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1323\u001b[0;31m       \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_inference_function\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcall_preflattened\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1324\u001b[0m     forward_backward = self._select_forward_and_backward_functions(\n\u001b[1;32m   1325\u001b[0m         \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py\u001b[0m in \u001b[0;36mcall_preflattened\u001b[0;34m(self, args)\u001b[0m\n\u001b[1;32m    214\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0mcall_preflattened\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mSequence\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTensor\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mAny\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    215\u001b[0m     \u001b[0;34m\"\"\"Calls with flattened tensor inputs and returns the structured output.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 216\u001b[0;31m     \u001b[0mflat_outputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcall_flat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    217\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfunction_type\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpack_output\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mflat_outputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    218\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py\u001b[0m in \u001b[0;36mcall_flat\u001b[0;34m(self, *args)\u001b[0m\n\u001b[1;32m    249\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mrecord\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstop_recording\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    250\u001b[0m           \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_bound_context\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecuting_eagerly\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 251\u001b[0;31m             outputs = self._bound_context.call_function(\n\u001b[0m\u001b[1;32m    252\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    253\u001b[0m                 \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/context.py\u001b[0m in \u001b[0;36mcall_function\u001b[0;34m(self, name, tensor_inputs, num_outputs)\u001b[0m\n\u001b[1;32m   1484\u001b[0m     \u001b[0mcancellation_context\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcancellation\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1485\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mcancellation_context\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1486\u001b[0;31m       outputs = execute.execute(\n\u001b[0m\u001b[1;32m   1487\u001b[0m           \u001b[0mname\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"utf-8\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1488\u001b[0m           \u001b[0mnum_outputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnum_outputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m     51\u001b[0m   \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     52\u001b[0m     \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 53\u001b[0;31m     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0m\u001b[1;32m     54\u001b[0m                                         inputs, attrs, num_outputs)\n\u001b[1;32m     55\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
          ]
        }
      ],
      "source": [
        "reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(\n",
        "    monitor='val_loss', factor=0.2, patience=3, min_lr=0.0001\n",
        ")\n",
        "\n",
        "callbacks = [\n",
        "    tf.keras.callbacks.EarlyStopping(patience=5),\n",
        "    tf.keras.callbacks.ModelCheckpoint('model.h5',save_best_only=True),\n",
        "    tf.keras.callbacks.TensorBoard(log_dir='logs'),\n",
        "    reduce_lr\n",
        "]\n",
        "results = model.fit(train_data, validation_data=valid_data, epochs=100, verbose=1)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "KJlesVZDi3Td"
      },
      "outputs": [],
      "source": [
        "model.save('/content/drive/MyDrive/ModelData')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "Tumour_detect = load_model('/content/drive/MyDrive/ModelData')\n"
      ],
      "metadata": {
        "id": "nHnnicj_JxjM"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "loss, acc = Tumour_detect.evaluate(test_data,verbose = 1)"
      ],
      "metadata": {
        "id": "nkj7NlywKOiK",
        "outputId": "7ef220c2-d54c-4405-f252-9161c479eaaa",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "20/20 [==============================] - 6s 287ms/step - loss: 0.5801 - accuracy: 0.7746\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Evaluation"
      ],
      "metadata": {
        "id": "YPukwveeI3Y0"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#imports\n",
        "from sklearn.metrics import classification_report,confusion_matrix\n",
        "import matplotlib.pyplot as plt\n",
        "from tensorflow.keras.preprocessing import image\n",
        "import seaborn as sns\n",
        "import numpy as np\n",
        "import cv2\n"
      ],
      "metadata": {
        "id": "2E1_Vb0fJV3p"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "res = results.history\n",
        "train_acc = res['accuracy']\n",
        "val_accuracy = res['val_accuracy']\n",
        "epochs = range(1, len(train_acc) + 1)\n",
        "\n",
        "line1 = plt.plot(epochs, val_accuracy, label = 'Validation/Test Accuracy')\n",
        "line2 = plt.plot(epochs, train_acc, label = 'Training Accuracy')\n",
        "\n",
        "plt.setp(line1, linewidth = 1.8, marker = 'o', markersize = 6.5)\n",
        "plt.setp(line2, linewidth = 1.8, marker = 's', markersize = 5)\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.grid(True)\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 449
        },
        "id": "Nhw72FVzyQgH",
        "outputId": "c7c4688e-ebc0-46bf-d812-a890dafc5ce8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install tensorflow\n",
        "!pip install reportlab\n",
        "!pip install datetime\n",
        "!pip install reportlab"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WtYkz6sTBWo2",
        "outputId": "961319cc-9a7a-403d-e1cd-e6f63301ac35"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: tensorflow in /usr/local/lib/python3.10/dist-packages (2.15.0)\n",
            "Requirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=23.5.26 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (23.5.26)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.5.4)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.9.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (16.0.6)\n",
            "Requirement already satisfied: ml-dtypes~=0.2.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: numpy<2.0.0,>=1.23.5 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.23.5)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.3.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from tensorflow) (23.2)\n",
            "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.20.3)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from tensorflow) (67.7.2)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.16.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (4.5.0)\n",
            "Requirement already satisfied: wrapt<1.15,>=1.11.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.14.1)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.35.0)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.60.0)\n",
            "Requirement already satisfied: tensorboard<2.16,>=2.15 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.15.1)\n",
            "Requirement already satisfied: tensorflow-estimator<2.16,>=2.15.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.15.0)\n",
            "Requirement already satisfied: keras<2.16,>=2.15.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.15.0)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from astunparse>=1.6.0->tensorflow) (0.42.0)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (2.17.3)\n",
            "Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (1.2.0)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (3.5.1)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (2.31.0)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (3.0.1)\n",
            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (5.3.2)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (0.3.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow) (1.3.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (2023.11.17)\n",
            "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/dist-packages (from werkzeug>=1.0.1->tensorboard<2.16,>=2.15->tensorflow) (2.1.3)\n",
            "Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (0.5.1)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow) (3.2.2)\n",
            "Requirement already satisfied: reportlab in /usr/local/lib/python3.10/dist-packages (4.0.8)\n",
            "Requirement already satisfied: pillow>=9.0.0 in /usr/local/lib/python3.10/dist-packages (from reportlab) (9.4.0)\n",
            "Requirement already satisfied: chardet in /usr/local/lib/python3.10/dist-packages (from reportlab) (5.2.0)\n",
            "Requirement already satisfied: datetime in /usr/local/lib/python3.10/dist-packages (5.4)\n",
            "Requirement already satisfied: zope.interface in /usr/local/lib/python3.10/dist-packages (from datetime) (6.1)\n",
            "Requirement already satisfied: pytz in /usr/local/lib/python3.10/dist-packages (from datetime) (2023.3.post1)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from zope.interface->datetime) (67.7.2)\n",
            "Requirement already satisfied: reportlab in /usr/local/lib/python3.10/dist-packages (4.0.8)\n",
            "Requirement already satisfied: pillow>=9.0.0 in /usr/local/lib/python3.10/dist-packages (from reportlab) (9.4.0)\n",
            "Requirement already satisfied: chardet in /usr/local/lib/python3.10/dist-packages (from reportlab) (5.2.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing import image\n",
        "import numpy as np\n",
        "from PIL import Image\n",
        "from tensorflow.keras.applications.mobilenet_v2 import preprocess_input\n",
        "from reportlab.pdfgen import canvas\n",
        "from google.colab import files\n",
        "from io import BytesIO\n",
        "from datetime import datetime\n",
        "\n",
        "# Load model\n",
        "Tumour_detect = tf.keras.models.load_model('/content/drive/MyDrive/ModelData')\n",
        "\n",
        "class_labels = {0: 'adenocarcinoma', 1: 'large.cell.carcinoma', 2: 'normal', 3: 'squamous.cell.carcinoma'}\n",
        "\n",
        "treatments_dict = {\n",
        "    0: \"Adenocarcinoma is often treated with a combination of surgery, chemotherapy, and targeted therapy.\",\n",
        "    1: \"Large cell carcinoma treatment may involve surgery, chemotherapy, and radiation therapy.\",\n",
        "    3: \"Squamous cell carcinoma treatment may include surgery, radiation therapy, and immunotherapy.\",\n",
        "}\n",
        "\n",
        "def preprocess_image(img_path):\n",
        "    img = image.load_img(img_path, target_size=(224, 224))\n",
        "    img_array = image.img_to_array(img)\n",
        "    img_array = preprocess_input(img_array)\n",
        "    return img_array\n",
        "\n",
        "def predict(image_path, model):\n",
        "    img_array = Image.open(image_path).convert(\"RGB\")\n",
        "    img_array = img_array.resize((224, 224))\n",
        "    img_array = np.array(img_array)\n",
        "    img_array = preprocess_input(img_array)\n",
        "    img_array = np.expand_dims(img_array, axis=0)\n",
        "    predictions = model.predict(img_array)\n",
        "    predicted_class = np.argmax(predictions)\n",
        "    return predicted_class\n",
        "\n",
        "# Colab widget for file uploading\n",
        "uploaded_file = files.upload()\n",
        "\n",
        "if len(uploaded_file) > 0:\n",
        "    # Get the first uploaded file\n",
        "    file_path = list(uploaded_file.keys())[0]\n",
        "\n",
        "    # Input additional information\n",
        "    nom = input(\"Entrez le nom du patient: \")\n",
        "    prenom = input(\"Entez le prénom du patient: \")\n",
        "    date_de_naissance = input(\"Entez la date de naissance du patient: \")\n",
        "\n",
        "    predicted_class = predict(file_path, Tumour_detect)\n",
        "\n",
        "    # Display the results\n",
        "    img = Image.open(file_path).convert(\"RGB\")\n",
        "    img = img.resize((224, 224))\n",
        "    display(img)\n",
        "\n",
        "    print(f\"Predicted: {class_labels[predicted_class]}\")\n",
        "\n",
        "    if predicted_class != 2:\n",
        "        recommended_treatments = treatments_dict.get(predicted_class, \"No specific treatments available.\")\n",
        "        print(\"Recommended Treatments:\")\n",
        "        print(recommended_treatments)\n",
        "    else:\n",
        "        print(\"No specific treatments are recommended. Regular health check-ups are advised.\")\n",
        "\n",
        "    # Save results in a PDF with a unique name based on timestamp\n",
        "    timestamp = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
        "    pdf_filename = f\"/content/drive/MyDrive/Rapports_Scan/Prediction_Report_{timestamp}.pdf\"\n",
        "\n",
        "    buffer = BytesIO()\n",
        "    pdf = canvas.Canvas(buffer)\n",
        "\n",
        "    # Add title and date of creation to PDF\n",
        "    pdf.drawString(100, 800, \"Rapport d'analyse de l'image radio\")\n",
        "    pdf.drawString(100, 780, f\"Date de consultation: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\")\n",
        "\n",
        "    # Add information to PDF\n",
        "    pdf.drawString(100, 760, f\"Nom: {nom}\")\n",
        "    pdf.drawString(100, 740, f\"Prénom: {prenom}\")\n",
        "    pdf.drawString(100, 720, f\"Date de naissance: {date_de_naissance}\")\n",
        "    pdf.drawString(100, 700, f\"Predicted Class: {class_labels[predicted_class]}\")\n",
        "\n",
        "    if predicted_class != 2:\n",
        "        pdf.drawString(100, 680, \"Traitement recommandé:\")\n",
        "        pdf.drawString(120, 660, recommended_treatments)\n",
        "\n",
        "    pdf.save()\n",
        "\n",
        "    # Move the buffer position back to the beginning\n",
        "    buffer.seek(0)\n",
        "\n",
        "    # Save the PDF to a file\n",
        "    with open(pdf_filename, \"wb\") as f:\n",
        "        f.write(buffer.read())\n",
        "\n",
        "    print(f\"Results saved in {pdf_filename}.\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 419
        },
        "id": "oSugEdRw9hIY",
        "outputId": "8f3198a2-0db5-409e-f951-48ce8bfb6a0c"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-ff09700d-95f0-4bf0-9e83-90b62ed56326\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-ff09700d-95f0-4bf0-9e83-90b62ed56326\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script>// Copyright 2017 Google LLC\n",
              "//\n",
              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
              "// you may not use this file except in compliance with the License.\n",
              "// You may obtain a copy of the License at\n",
              "//\n",
              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
              "//\n",
              "// Unless required by applicable law or agreed to in writing, software\n",
              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
              "// See the License for the specific language governing permissions and\n",
              "// limitations under the License.\n",
              "\n",
              "/**\n",
              " * @fileoverview Helpers for google.colab Python module.\n",
              " */\n",
              "(function(scope) {\n",
              "function span(text, styleAttributes = {}) {\n",
              "  const element = document.createElement('span');\n",
              "  element.textContent = text;\n",
              "  for (const key of Object.keys(styleAttributes)) {\n",
              "    element.style[key] = styleAttributes[key];\n",
              "  }\n",
              "  return element;\n",
              "}\n",
              "\n",
              "// Max number of bytes which will be uploaded at a time.\n",
              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
              "\n",
              "function _uploadFiles(inputId, outputId) {\n",
              "  const steps = uploadFilesStep(inputId, outputId);\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  // Cache steps on the outputElement to make it available for the next call\n",
              "  // to uploadFilesContinue from Python.\n",
              "  outputElement.steps = steps;\n",
              "\n",
              "  return _uploadFilesContinue(outputId);\n",
              "}\n",
              "\n",
              "// This is roughly an async generator (not supported in the browser yet),\n",
              "// where there are multiple asynchronous steps and the Python side is going\n",
              "// to poll for completion of each step.\n",
              "// This uses a Promise to block the python side on completion of each step,\n",
              "// then passes the result of the previous step as the input to the next step.\n",
              "function _uploadFilesContinue(outputId) {\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  const steps = outputElement.steps;\n",
              "\n",
              "  const next = steps.next(outputElement.lastPromiseValue);\n",
              "  return Promise.resolve(next.value.promise).then((value) => {\n",
              "    // Cache the last promise value to make it available to the next\n",
              "    // step of the generator.\n",
              "    outputElement.lastPromiseValue = value;\n",
              "    return next.value.response;\n",
              "  });\n",
              "}\n",
              "\n",
              "/**\n",
              " * Generator function which is called between each async step of the upload\n",
              " * process.\n",
              " * @param {string} inputId Element ID of the input file picker element.\n",
              " * @param {string} outputId Element ID of the output display.\n",
              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
              " */\n",
              "function* uploadFilesStep(inputId, outputId) {\n",
              "  const inputElement = document.getElementById(inputId);\n",
              "  inputElement.disabled = false;\n",
              "\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  outputElement.innerHTML = '';\n",
              "\n",
              "  const pickedPromise = new Promise((resolve) => {\n",
              "    inputElement.addEventListener('change', (e) => {\n",
              "      resolve(e.target.files);\n",
              "    });\n",
              "  });\n",
              "\n",
              "  const cancel = document.createElement('button');\n",
              "  inputElement.parentElement.appendChild(cancel);\n",
              "  cancel.textContent = 'Cancel upload';\n",
              "  const cancelPromise = new Promise((resolve) => {\n",
              "    cancel.onclick = () => {\n",
              "      resolve(null);\n",
              "    };\n",
              "  });\n",
              "\n",
              "  // Wait for the user to pick the files.\n",
              "  const files = yield {\n",
              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
              "    response: {\n",
              "      action: 'starting',\n",
              "    }\n",
              "  };\n",
              "\n",
              "  cancel.remove();\n",
              "\n",
              "  // Disable the input element since further picks are not allowed.\n",
              "  inputElement.disabled = true;\n",
              "\n",
              "  if (!files) {\n",
              "    return {\n",
              "      response: {\n",
              "        action: 'complete',\n",
              "      }\n",
              "    };\n",
              "  }\n",
              "\n",
              "  for (const file of files) {\n",
              "    const li = document.createElement('li');\n",
              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
              "    li.append(span(\n",
              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
              "        `last modified: ${\n",
              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
              "                                    'n/a'} - `));\n",
              "    const percent = span('0% done');\n",
              "    li.appendChild(percent);\n",
              "\n",
              "    outputElement.appendChild(li);\n",
              "\n",
              "    const fileDataPromise = new Promise((resolve) => {\n",
              "      const reader = new FileReader();\n",
              "      reader.onload = (e) => {\n",
              "        resolve(e.target.result);\n",
              "      };\n",
              "      reader.readAsArrayBuffer(file);\n",
              "    });\n",
              "    // Wait for the data to be ready.\n",
              "    let fileData = yield {\n",
              "      promise: fileDataPromise,\n",
              "      response: {\n",
              "        action: 'continue',\n",
              "      }\n",
              "    };\n",
              "\n",
              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
              "    let position = 0;\n",
              "    do {\n",
              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
              "      const chunk = new Uint8Array(fileData, position, length);\n",
              "      position += length;\n",
              "\n",
              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
              "      yield {\n",
              "        response: {\n",
              "          action: 'append',\n",
              "          file: file.name,\n",
              "          data: base64,\n",
              "        },\n",
              "      };\n",
              "\n",
              "      let percentDone = fileData.byteLength === 0 ?\n",
              "          100 :\n",
              "          Math.round((position / fileData.byteLength) * 100);\n",
              "      percent.textContent = `${percentDone}% done`;\n",
              "\n",
              "    } while (position < fileData.byteLength);\n",
              "  }\n",
              "\n",
              "  // All done.\n",
              "  yield {\n",
              "    response: {\n",
              "      action: 'complete',\n",
              "    }\n",
              "  };\n",
              "}\n",
              "\n",
              "scope.google = scope.google || {};\n",
              "scope.google.colab = scope.google.colab || {};\n",
              "scope.google.colab._files = {\n",
              "  _uploadFiles,\n",
              "  _uploadFilesContinue,\n",
              "};\n",
              "})(self);\n",
              "</script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving testImageNormal.png to testImageNormal.png\n",
            "Entrez le nom du patient: Nom du patient\n",
            "Entez le prénom du patient: Prénom du patient\n",
            "Entez la date de naissance du patient: xx-xx-xxxx\n",
            "1/1 [==============================] - 0s 171ms/step\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=224x224>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Predicted: normal\n",
            "No specific treatments are recommended. Regular health check-ups are advised.\n",
            "Results saved in /content/drive/MyDrive/Rapports_Scan/Prediction_Report_20240106111633.pdf.\n"
          ]
        }
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}