{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "!unzip DATASET-JPG.zip -d /content/dataset"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VbTgMw6NF3Dp",
        "outputId": "042d00ce-9872-49ab-d273-aec5ed83a0ab"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "unzip:  cannot find or open DATASET-JPG.zip, DATASET-JPG.zip.zip or DATASET-JPG.zip.ZIP.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip DATASET JPG.zip -d /content/dataset"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vxdpYiN2HD-n",
        "outputId": "f363a235-0c14-41c6-842b-bad3d71525c1"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "unzip:  cannot find or open DATASET, DATASET.zip or DATASET.ZIP.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!ls /content"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zwt2SAPrHek4",
        "outputId": "ef3cd054-f199-449d-8a2b-b762eae7bfa3"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "'DATASET JPG.zip'   sample_data\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip \"DATASET JPG.zip\" -d /content/dataset"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fzuab4slHoYs",
        "outputId": "9c0b278a-7e1f-46e3-b2a2-5d9a8f594958"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Archive:  DATASET JPG.zip\n",
            "   creating: /content/dataset/DATASET JPG/\n",
            "   creating: /content/dataset/DATASET JPG/withmask/\n",
            "  inflating: /content/dataset/DATASET JPG/withmask/011.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/012.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/028.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/035.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/043.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/053.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/079.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/086.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/094.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/095.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/100.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/103.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/111.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/139.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/149.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/152.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/161.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/165.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/172.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/183.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/186.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/192.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/199.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/203.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/207.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/217.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/229.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/248.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/withmask/254.jpg  \n",
            "   creating: /content/dataset/DATASET JPG/without/\n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD179.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD223.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD251.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD326.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD348.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD353.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD365.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD370.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD379.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD380.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD383.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD391.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD473.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD474.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD480.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD756.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD771.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD793.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD797.jpg  \n",
            "  inflating: /content/dataset/DATASET JPG/without/CMFD813.jpg  \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!ls \"/content/dataset/DATASET JPG\""
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5i0-OkOBH2oP",
        "outputId": "cf8fa086-e517-487e-822a-536c35337393"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "withmask  without\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "base_dir = \"/content/dataset/DATASET JPG\"\n",
        "\n",
        "datagen = ImageDataGenerator(\n",
        "    rescale=1./255,\n",
        "    validation_split=0.2\n",
        ")\n",
        "\n",
        "train_data = datagen.flow_from_directory(\n",
        "    base_dir,\n",
        "    target_size=(128,128),\n",
        "    batch_size=32,\n",
        "    class_mode='binary',\n",
        "    subset='training'\n",
        ")\n",
        "\n",
        "val_data = datagen.flow_from_directory(\n",
        "    base_dir,\n",
        "    target_size=(128,128),\n",
        "    batch_size=32,\n",
        "    class_mode='binary',\n",
        "    subset='validation'\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1tMWsOceH77E",
        "outputId": "6ed3471a-02e9-4bcb-9179-e9fb96e71aff"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 40 images belonging to 2 classes.\n",
            "Found 9 images belonging to 2 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\n",
        "\n",
        "model = Sequential([\n",
        "    Conv2D(32, (3,3), activation='relu', input_shape=(128,128,3)),\n",
        "    MaxPooling2D(2,2),\n",
        "\n",
        "    Conv2D(64, (3,3), activation='relu'),\n",
        "    MaxPooling2D(2,2),\n",
        "\n",
        "    Conv2D(128, (3,3), activation='relu'),\n",
        "    MaxPooling2D(2,2),\n",
        "\n",
        "    Flatten(),\n",
        "    Dense(128, activation='relu'),\n",
        "    Dense(1, activation='sigmoid')\n",
        "])\n",
        "\n",
        "model.compile(\n",
        "    optimizer='adam',\n",
        "    loss='binary_crossentropy',\n",
        "    metrics=['accuracy']\n",
        ")\n",
        "\n",
        "model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 482
        },
        "id": "7CFbl2ZDIYV0",
        "outputId": "3347e53e-e9d7-4cc6-99af-fcde90da4bb8"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
            "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m63\u001b[0m, \u001b[38;5;34m63\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m61\u001b[0m, \u001b[38;5;34m61\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │        \u001b[38;5;34m73,856\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m25088\u001b[0m)          │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │     \u001b[38;5;34m3,211,392\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │           \u001b[38;5;34m129\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">126</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">126</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">63</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">63</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">61</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">61</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">28</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">28</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">25088</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │     <span style=\"color: #00af00; text-decoration-color: #00af00\">3,211,392</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">129</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m3,304,769\u001b[0m (12.61 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">3,304,769</span> (12.61 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m3,304,769\u001b[0m (12.61 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">3,304,769</span> (12.61 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "history = model.fit(\n",
        "    train_data,\n",
        "    validation_data=val_data,\n",
        "    epochs=10\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xjG7tA_-I7oI",
        "outputId": "9e0144b4-35e1-4dac-eca6-a258046a3f72"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
            "  self._warn_if_super_not_called()\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 2s/step - accuracy: 0.4917 - loss: 0.7700 - val_accuracy: 0.5556 - val_loss: 0.6844\n",
            "Epoch 2/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2s/step - accuracy: 0.2833 - loss: 0.7607 - val_accuracy: 0.4444 - val_loss: 0.6972\n",
            "Epoch 3/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1s/step - accuracy: 0.3917 - loss: 0.7034 - val_accuracy: 0.8889 - val_loss: 0.6769\n",
            "Epoch 4/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 339ms/step - accuracy: 1.0000 - loss: 0.6633 - val_accuracy: 0.5556 - val_loss: 0.6674\n",
            "Epoch 5/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 959ms/step - accuracy: 0.6083 - loss: 0.6415 - val_accuracy: 0.7778 - val_loss: 0.6279\n",
            "Epoch 6/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 347ms/step - accuracy: 0.9729 - loss: 0.5820 - val_accuracy: 0.8889 - val_loss: 0.5684\n",
            "Epoch 7/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 960ms/step - accuracy: 1.0000 - loss: 0.4850 - val_accuracy: 0.8889 - val_loss: 0.4871\n",
            "Epoch 8/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step - accuracy: 0.8833 - loss: 0.3877 - val_accuracy: 0.8889 - val_loss: 0.4406\n",
            "Epoch 9/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1s/step - accuracy: 0.9667 - loss: 0.1863 - val_accuracy: 1.0000 - val_loss: 0.2877\n",
            "Epoch 10/10\n",
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/step - accuracy: 1.0000 - loss: 0.1169 - val_accuracy: 0.8889 - val_loss: 0.1863\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "# Accuracy\n",
        "plt.plot(history.history['accuracy'], label='Train Accuracy')\n",
        "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
        "plt.title('Model Accuracy')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend()\n",
        "plt.show()\n",
        "\n",
        "# Loss\n",
        "plt.plot(history.history['loss'], label='Train Loss')\n",
        "plt.plot(history.history['val_loss'], label='Validation Loss')\n",
        "plt.title('Model Loss')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 927
        },
        "id": "3RZvAr6NJomh",
        "outputId": "5d769f24-7c33-49a2-a330-b553b606ff1f"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "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": [
        "model.save('/content/face_mask_model.keras')"
      ],
      "metadata": {
        "id": "fiS00p5WKYQA"
      },
      "execution_count": 22,
      "outputs": []
    }
  ]
}