{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# **CNN Experiment 6 - Additional Convolutional Layer**"
      ],
      "metadata": {
        "id": "Sbj7i3fO5Ad_"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 1. Google Drive and Dataset Setup"
      ],
      "metadata": {
        "id": "oKSttFtI5I6g"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount(\"/content/drive\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Sw0Vl5JgvbyO",
        "outputId": "08d23d75-12bb-4958-bc99-77222ebd1299"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import zipfile\n",
        "\n",
        "zip_path = \"/content/drive/MyDrive/PlantPathology_Split.zip\"\n",
        "extract_path = \"/content\"\n",
        "\n",
        "with zipfile.ZipFile(zip_path, \"r\") as zip_ref:\n",
        "    zip_ref.extractall(\"/content\")\n",
        "\n",
        "print(\"Unzip completed.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aU0-O3E6If7i",
        "outputId": "6a17bd85-9425-43f8-d428-f22388bfbd4d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Unzip completed.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 2. Five-Class Dataset Preparation\n"
      ],
      "metadata": {
        "id": "0iv3O8qO5VpM"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import shutil\n",
        "\n",
        "source_dir = \"/content/PlantPathology_Split\"\n",
        "target_dir = \"/content/PlantPathology_5Classes\"\n",
        "\n",
        "selected_classes = [\n",
        "    \"healthy\",\n",
        "    \"scab\",\n",
        "    \"frog_eye_leaf_spot\",\n",
        "    \"rust\",\n",
        "    \"powdery_mildew\"\n",
        "]\n",
        "\n",
        "splits = [\"train\", \"valid\", \"test\"]\n",
        "\n",
        "# Remove old version if it already exists\n",
        "if os.path.exists(target_dir):\n",
        "    shutil.rmtree(target_dir)\n",
        "\n",
        "# Copy only the five required classes\n",
        "for split in splits:\n",
        "    for class_name in selected_classes:\n",
        "\n",
        "        source_class_dir = os.path.join(\n",
        "            source_dir,\n",
        "            split,\n",
        "            class_name\n",
        "        )\n",
        "\n",
        "        target_class_dir = os.path.join(\n",
        "            target_dir,\n",
        "            split,\n",
        "            class_name\n",
        "        )\n",
        "\n",
        "        if not os.path.exists(source_class_dir):\n",
        "            print(f\"Missing folder: {source_class_dir}\")\n",
        "            continue\n",
        "\n",
        "        shutil.copytree(\n",
        "            source_class_dir,\n",
        "            target_class_dir\n",
        "        )\n",
        "\n",
        "print(\"Five-class dataset created.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7ItFYHBXIw2Q",
        "outputId": "3ce394cb-885e-4195-ea44-e92a5195af03"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Five-class dataset created.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 3. Dataset Distribution"
      ],
      "metadata": {
        "id": "7XM6t0IF5pjz"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "for split in splits:\n",
        "    print(f\"\\n{split.upper()}\")\n",
        "\n",
        "    total = 0\n",
        "\n",
        "    for class_name in selected_classes:\n",
        "        class_path = os.path.join(\n",
        "            target_dir,\n",
        "            split,\n",
        "            class_name\n",
        "        )\n",
        "\n",
        "        image_count = len([\n",
        "            file_name\n",
        "            for file_name in os.listdir(class_path)\n",
        "            if os.path.isfile(\n",
        "                os.path.join(class_path, file_name)\n",
        "            )\n",
        "        ])\n",
        "\n",
        "        total += image_count\n",
        "\n",
        "        print(f\"{class_name}: {image_count}\")\n",
        "\n",
        "    print(f\"Total: {total}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Vd601LX1I72b",
        "outputId": "03b60fb6-3749-4537-dbee-c7553c2902a2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "TRAIN\n",
            "healthy: 2074\n",
            "scab: 2334\n",
            "frog_eye_leaf_spot: 1448\n",
            "rust: 864\n",
            "powdery_mildew: 587\n",
            "Total: 7307\n",
            "\n",
            "VALID\n",
            "healthy: 444\n",
            "scab: 500\n",
            "frog_eye_leaf_spot: 310\n",
            "rust: 185\n",
            "powdery_mildew: 125\n",
            "Total: 1564\n",
            "\n",
            "TEST\n",
            "healthy: 445\n",
            "scab: 500\n",
            "frog_eye_leaf_spot: 310\n",
            "rust: 186\n",
            "powdery_mildew: 126\n",
            "Total: 1567\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 4. TensorFlow Data Pipeline"
      ],
      "metadata": {
        "id": "8JRAL6Vn5uc0"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "\n",
        "IMG_SIZE = (512, 512)\n",
        "BATCH_SIZE = 32\n",
        "\n",
        "train_dir = \"/content/PlantPathology_5Classes/train\"\n",
        "valid_dir = \"/content/PlantPathology_5Classes/valid\"\n",
        "test_dir = \"/content/PlantPathology_5Classes/test\"\n",
        "\n",
        "train_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "    train_dir,\n",
        "    image_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    label_mode=\"int\",\n",
        "    shuffle=True,\n",
        "    seed=42\n",
        ")\n",
        "\n",
        "valid_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "    valid_dir,\n",
        "    image_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    label_mode=\"int\",\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "test_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "    test_dir,\n",
        "    image_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    label_mode=\"int\",\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "class_names = train_ds.class_names\n",
        "\n",
        "print(\"\\nClasses:\")\n",
        "print(class_names)\n",
        "\n",
        "print(\"\\nNumber of classes:\", len(class_names))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JVa-slm2JAtn",
        "outputId": "9f9c1d3d-3620-474b-bdca-4df7d977e34d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 7307 files belonging to 5 classes.\n",
            "Found 1564 files belonging to 5 classes.\n",
            "Found 1567 files belonging to 5 classes.\n",
            "\n",
            "Classes:\n",
            "['frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\n",
            "\n",
            "Number of classes: 5\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 5. Dataset Performance Optimisation"
      ],
      "metadata": {
        "id": "xhWtwZwi50cF"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "AUTOTUNE = tf.data.AUTOTUNE\n",
        "\n",
        "train_ds = train_ds.prefetch(\n",
        "    buffer_size=AUTOTUNE\n",
        ")\n",
        "\n",
        "valid_ds = valid_ds.prefetch(\n",
        "    buffer_size=AUTOTUNE\n",
        ")\n",
        "\n",
        "test_ds = test_ds.prefetch(\n",
        "    buffer_size=AUTOTUNE\n",
        ")"
      ],
      "metadata": {
        "id": "DAiQ_LIXJgZG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 6. Data Augmentation\n"
      ],
      "metadata": {
        "id": "1bbj7Ux-Q2l3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras import layers, models\n",
        "\n",
        "data_augmentation = models.Sequential([\n",
        "    layers.RandomFlip(\"horizontal\"),\n",
        "    layers.RandomRotation(0.1),\n",
        "    layers.RandomZoom(0.1)\n",
        "], name=\"data_augmentation\")"
      ],
      "metadata": {
        "id": "KEoPAuaESM3f"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 7. Experiment 6 CNN Architecture"
      ],
      "metadata": {
        "id": "74rwYnFFSTjN"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras import layers, models\n",
        "\n",
        "num_classes = len(class_names)\n",
        "\n",
        "experiment6_model = models.Sequential([\n",
        "    layers.Input(shape=(512, 512, 3)),\n",
        "\n",
        "    data_augmentation,\n",
        "\n",
        "    layers.Rescaling(1./255),\n",
        "\n",
        "    layers.Conv2D(32, 3, activation=\"relu\"),\n",
        "    layers.MaxPooling2D(),\n",
        "\n",
        "    layers.Conv2D(64, 3, activation=\"relu\"),\n",
        "    layers.MaxPooling2D(),\n",
        "\n",
        "    layers.Conv2D(128, 3, activation=\"relu\"),\n",
        "    layers.MaxPooling2D(),\n",
        "\n",
        "    layers.Conv2D(256, 3, activation=\"relu\"),\n",
        "    layers.MaxPooling2D(),\n",
        "\n",
        "    layers.Flatten(),\n",
        "\n",
        "    layers.Dense(128, activation=\"relu\"),\n",
        "    layers.Dropout(0.3),\n",
        "\n",
        "    layers.Dense(num_classes, activation=\"softmax\")\n",
        "], name=\"experiment6_cnn\")\n",
        "\n",
        "experiment6_model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 577
        },
        "id": "P5ON57sTkftU",
        "outputId": "d09a18a7-2062-44ff-9a6b-150b4a5333e7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"experiment6_cnn\"\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: \"experiment6_cnn\"</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",
              "│ data_augmentation (\u001b[38;5;33mSequential\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ rescaling (\u001b[38;5;33mRescaling\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m510\u001b[0m, \u001b[38;5;34m510\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;34m255\u001b[0m, \u001b[38;5;34m255\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;34m253\u001b[0m, \u001b[38;5;34m253\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;34m126\u001b[0m, \u001b[38;5;34m126\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;34m124\u001b[0m, \u001b[38;5;34m124\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;34m62\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m60\u001b[0m, \u001b[38;5;34m60\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │       \u001b[38;5;34m295,168\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_3 (\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;34m256\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;34m230400\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;34m29,491,328\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m)              │           \u001b[38;5;34m645\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",
              "│ data_augmentation (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Sequential</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ rescaling (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Rescaling</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</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\">510</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">510</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\">255</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">255</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\">253</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">253</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\">126</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">126</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\">124</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">124</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\">62</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">62</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_3 (<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\">60</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">60</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_3 (<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\">256</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\">230400</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\">29,491,328</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</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\">0</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\">5</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">645</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m29,880,389\u001b[0m (113.98 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\">29,880,389</span> (113.98 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m29,880,389\u001b[0m (113.98 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\">29,880,389</span> (113.98 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": "markdown",
      "source": [
        "# 8. Model Compilation"
      ],
      "metadata": {
        "id": "jvebUxgvmfZ3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.optimizers import Adam\n",
        "\n",
        "experiment6_model.compile(\n",
        "    optimizer=Adam(learning_rate=0.0003),\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "    metrics=[\"accuracy\"]\n",
        ")"
      ],
      "metadata": {
        "id": "W_UYNLmFmt7U"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 9. Training Callbacks"
      ],
      "metadata": {
        "id": "Dma-yagpTsAt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.callbacks import (\n",
        "    EarlyStopping,\n",
        "    ModelCheckpoint\n",
        ")\n",
        "\n",
        "early_stop = EarlyStopping(\n",
        "    monitor=\"val_loss\",\n",
        "    patience=5,\n",
        "    restore_best_weights=True,\n",
        "    verbose=1\n",
        ")\n",
        "\n",
        "checkpoint = ModelCheckpoint(\n",
        "    filepath=\"/content/drive/MyDrive/experiment6_cnn_best.keras\",\n",
        "    monitor=\"val_loss\",\n",
        "    save_best_only=True,\n",
        "    verbose=0\n",
        ")\n",
        "\n",
        "callbacks_experiment6 = [\n",
        "    early_stop,\n",
        "    checkpoint\n",
        "]"
      ],
      "metadata": {
        "id": "TDUEPMO3mzPY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 10. Model Training\n"
      ],
      "metadata": {
        "id": "A01eBBYNm7KH"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "history_experiment6 = experiment6_model.fit(\n",
        "    train_ds,\n",
        "    validation_data=valid_ds,\n",
        "    epochs=30,\n",
        "    callbacks=callbacks_experiment6,\n",
        "    verbose=1\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sCV2uCaNnGNL",
        "outputId": "601e26c8-c622-4858-9c7f-62959821caf5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 297ms/step - accuracy: 0.3655 - loss: 1.4097 - val_accuracy: 0.4853 - val_loss: 1.1971\n",
            "Epoch 2/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m65s\u001b[0m 281ms/step - accuracy: 0.5495 - loss: 1.0871 - val_accuracy: 0.6234 - val_loss: 0.8895\n",
            "Epoch 3/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 320ms/step - accuracy: 0.6421 - loss: 0.8931 - val_accuracy: 0.6643 - val_loss: 0.7968\n",
            "Epoch 4/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 301ms/step - accuracy: 0.6689 - loss: 0.8173 - val_accuracy: 0.7014 - val_loss: 0.7160\n",
            "Epoch 5/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 298ms/step - accuracy: 0.6969 - loss: 0.7579 - val_accuracy: 0.7168 - val_loss: 0.6776\n",
            "Epoch 6/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 302ms/step - accuracy: 0.7114 - loss: 0.7261 - val_accuracy: 0.7295 - val_loss: 0.6594\n",
            "Epoch 7/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m77s\u001b[0m 281ms/step - accuracy: 0.7268 - loss: 0.6848 - val_accuracy: 0.6758 - val_loss: 0.7593\n",
            "Epoch 8/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 298ms/step - accuracy: 0.7376 - loss: 0.6689 - val_accuracy: 0.7263 - val_loss: 0.6422\n",
            "Epoch 9/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m65s\u001b[0m 283ms/step - accuracy: 0.7412 - loss: 0.6462 - val_accuracy: 0.7289 - val_loss: 0.6614\n",
            "Epoch 10/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 287ms/step - accuracy: 0.7572 - loss: 0.6125 - val_accuracy: 0.7449 - val_loss: 0.6529\n",
            "Epoch 11/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 300ms/step - accuracy: 0.7716 - loss: 0.5788 - val_accuracy: 0.7653 - val_loss: 0.6045\n",
            "Epoch 12/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 293ms/step - accuracy: 0.7798 - loss: 0.5575 - val_accuracy: 0.8012 - val_loss: 0.5101\n",
            "Epoch 13/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 287ms/step - accuracy: 0.7912 - loss: 0.5402 - val_accuracy: 0.7692 - val_loss: 0.5994\n",
            "Epoch 14/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 287ms/step - accuracy: 0.7924 - loss: 0.5230 - val_accuracy: 0.7474 - val_loss: 0.6636\n",
            "Epoch 15/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 290ms/step - accuracy: 0.8033 - loss: 0.5114 - val_accuracy: 0.7973 - val_loss: 0.5160\n",
            "Epoch 16/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 293ms/step - accuracy: 0.8161 - loss: 0.4734 - val_accuracy: 0.8178 - val_loss: 0.5002\n",
            "Epoch 17/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 305ms/step - accuracy: 0.8330 - loss: 0.4391 - val_accuracy: 0.8402 - val_loss: 0.4406\n",
            "Epoch 18/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m65s\u001b[0m 282ms/step - accuracy: 0.8418 - loss: 0.4308 - val_accuracy: 0.8107 - val_loss: 0.5250\n",
            "Epoch 19/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m85s\u001b[0m 297ms/step - accuracy: 0.8529 - loss: 0.3938 - val_accuracy: 0.8574 - val_loss: 0.3851\n",
            "Epoch 20/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 297ms/step - accuracy: 0.8612 - loss: 0.3864 - val_accuracy: 0.8811 - val_loss: 0.3713\n",
            "Epoch 21/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 296ms/step - accuracy: 0.8692 - loss: 0.3584 - val_accuracy: 0.8689 - val_loss: 0.3690\n",
            "Epoch 22/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 291ms/step - accuracy: 0.8878 - loss: 0.3152 - val_accuracy: 0.8760 - val_loss: 0.3569\n",
            "Epoch 23/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 307ms/step - accuracy: 0.8956 - loss: 0.3083 - val_accuracy: 0.8862 - val_loss: 0.3071\n",
            "Epoch 24/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 302ms/step - accuracy: 0.9028 - loss: 0.2754 - val_accuracy: 0.8836 - val_loss: 0.3269\n",
            "Epoch 25/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m77s\u001b[0m 280ms/step - accuracy: 0.9016 - loss: 0.2860 - val_accuracy: 0.8670 - val_loss: 0.4058\n",
            "Epoch 26/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 287ms/step - accuracy: 0.9052 - loss: 0.2832 - val_accuracy: 0.8740 - val_loss: 0.3479\n",
            "Epoch 27/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 291ms/step - accuracy: 0.9172 - loss: 0.2449 - val_accuracy: 0.8932 - val_loss: 0.3503\n",
            "Epoch 28/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 288ms/step - accuracy: 0.9093 - loss: 0.2539 - val_accuracy: 0.8964 - val_loss: 0.3130\n",
            "Epoch 28: early stopping\n",
            "Restoring model weights from the end of the best epoch: 23.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 11. Training Results"
      ],
      "metadata": {
        "id": "5L_2yO0EfEsf"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from IPython.display import display\n",
        "\n",
        "max_epochs = 30\n",
        "epochs_completed = len(history_experiment6.history[\"loss\"])\n",
        "\n",
        "# Best epoch based on the lowest validation loss\n",
        "best_epoch = int(\n",
        "    np.argmin(history_experiment6.history[\"val_loss\"]) + 1\n",
        ")\n",
        "\n",
        "best_val_loss = history_experiment6.history[\"val_loss\"][best_epoch - 1]\n",
        "best_val_accuracy = history_experiment6.history[\"val_accuracy\"][best_epoch - 1]\n",
        "\n",
        "train_loss_at_best_epoch = history_experiment6.history[\"loss\"][best_epoch - 1]\n",
        "train_accuracy_at_best_epoch = history_experiment6.history[\"accuracy\"][best_epoch - 1]\n",
        "\n",
        "# Highest validation accuracy\n",
        "highest_val_accuracy = max(\n",
        "    history_experiment6.history[\"val_accuracy\"]\n",
        ")\n",
        "\n",
        "highest_val_accuracy_epoch = int(\n",
        "    np.argmax(history_experiment6.history[\"val_accuracy\"]) + 1\n",
        ")\n",
        "\n",
        "# EarlyStopping and checkpoint\n",
        "early_stopping_activated = epochs_completed < max_epochs\n",
        "\n",
        "checkpoint_path = (\n",
        "    \"/content/drive/MyDrive/experiment6_cnn_best.keras\"\n",
        ")\n",
        "\n",
        "checkpoint_saved = os.path.exists(checkpoint_path)\n",
        "\n",
        "summary_table = pd.DataFrame({\n",
        "    \"Metric\": [\n",
        "        \"Maximum Epochs\",\n",
        "        \"Epochs Completed\",\n",
        "        \"Early Stopping Activated\",\n",
        "        \"Best Checkpoint Epoch\",\n",
        "        \"Training Accuracy at Best Epoch\",\n",
        "        \"Validation Accuracy at Best Epoch\",\n",
        "        \"Training Loss at Best Epoch\",\n",
        "        \"Best Validation Loss\",\n",
        "        \"Highest Validation Accuracy\",\n",
        "        \"Highest Validation Accuracy Epoch\",\n",
        "        \"Best Checkpoint Saved\"\n",
        "    ],\n",
        "    \"Result\": [\n",
        "        max_epochs,\n",
        "        epochs_completed,\n",
        "        \"Yes\" if early_stopping_activated else \"No\",\n",
        "        best_epoch,\n",
        "        f\"{train_accuracy_at_best_epoch * 100:.2f}%\",\n",
        "        f\"{best_val_accuracy * 100:.2f}%\",\n",
        "        f\"{train_loss_at_best_epoch:.4f}\",\n",
        "        f\"{best_val_loss:.4f}\",\n",
        "        f\"{highest_val_accuracy * 100:.2f}%\",\n",
        "        highest_val_accuracy_epoch,\n",
        "        \"Yes\" if checkpoint_saved else \"No\"\n",
        "    ]\n",
        "})\n",
        "\n",
        "display(\n",
        "    summary_table.style\n",
        "    .set_caption(\n",
        "        \"Experiment 6 CNN with Additional Convolutional Block Results\"\n",
        "    )\n",
        "    .hide(axis=\"index\")\n",
        "    .set_properties(**{\n",
        "        \"text-align\": \"center\",\n",
        "        \"font-size\": \"14px\"\n",
        "    })\n",
        "    .set_table_styles([\n",
        "        {\n",
        "            \"selector\": \"caption\",\n",
        "            \"props\": [\n",
        "                (\"font-size\", \"15px\"),\n",
        "                (\"font-weight\", \"bold\"),\n",
        "                (\"text-align\", \"left\"),\n",
        "                (\"padding-bottom\", \"10px\"),\n",
        "                (\"white-space\", \"nowrap\")\n",
        "            ]\n",
        "        },\n",
        "        {\n",
        "            \"selector\": \"th\",\n",
        "            \"props\": [\n",
        "                (\"border\", \"1px solid black\"),\n",
        "                (\"font-weight\", \"bold\"),\n",
        "                (\"text-align\", \"center\"),\n",
        "                (\"padding\", \"9px\")\n",
        "            ]\n",
        "        },\n",
        "        {\n",
        "            \"selector\": \"td\",\n",
        "            \"props\": [\n",
        "                (\"border\", \"1px solid black\"),\n",
        "                (\"padding\", \"9px\")\n",
        "            ]\n",
        "        }\n",
        "    ])\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 481
        },
        "id": "1czy2PEbNj6F",
        "outputId": "be61d0ed-0f53-46f4-e24e-96e7b821e9a0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<pandas.io.formats.style.Styler at 0x7a6fc7ed9d00>"
            ],
            "text/html": [
              "<style type=\"text/css\">\n",
              "#T_0ad47 caption {\n",
              "  font-size: 15px;\n",
              "  font-weight: bold;\n",
              "  text-align: left;\n",
              "  padding-bottom: 10px;\n",
              "  white-space: nowrap;\n",
              "}\n",
              "#T_0ad47 th {\n",
              "  border: 1px solid black;\n",
              "  font-weight: bold;\n",
              "  text-align: center;\n",
              "  padding: 9px;\n",
              "}\n",
              "#T_0ad47 td {\n",
              "  border: 1px solid black;\n",
              "  padding: 9px;\n",
              "}\n",
              "#T_0ad47_row0_col0, #T_0ad47_row0_col1, #T_0ad47_row1_col0, #T_0ad47_row1_col1, #T_0ad47_row2_col0, #T_0ad47_row2_col1, #T_0ad47_row3_col0, #T_0ad47_row3_col1, #T_0ad47_row4_col0, #T_0ad47_row4_col1, #T_0ad47_row5_col0, #T_0ad47_row5_col1, #T_0ad47_row6_col0, #T_0ad47_row6_col1, #T_0ad47_row7_col0, #T_0ad47_row7_col1, #T_0ad47_row8_col0, #T_0ad47_row8_col1, #T_0ad47_row9_col0, #T_0ad47_row9_col1, #T_0ad47_row10_col0, #T_0ad47_row10_col1 {\n",
              "  text-align: center;\n",
              "  font-size: 14px;\n",
              "}\n",
              "</style>\n",
              "<table id=\"T_0ad47\" class=\"dataframe\">\n",
              "  <caption>Experiment 6 CNN with Additional Convolutional Block Results</caption>\n",
              "  <thead>\n",
              "    <tr>\n",
              "      <th id=\"T_0ad47_level0_col0\" class=\"col_heading level0 col0\" >Metric</th>\n",
              "      <th id=\"T_0ad47_level0_col1\" class=\"col_heading level0 col1\" >Result</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row0_col0\" class=\"data row0 col0\" >Maximum Epochs</td>\n",
              "      <td id=\"T_0ad47_row0_col1\" class=\"data row0 col1\" >30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row1_col0\" class=\"data row1 col0\" >Epochs Completed</td>\n",
              "      <td id=\"T_0ad47_row1_col1\" class=\"data row1 col1\" >28</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row2_col0\" class=\"data row2 col0\" >Early Stopping Activated</td>\n",
              "      <td id=\"T_0ad47_row2_col1\" class=\"data row2 col1\" >Yes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row3_col0\" class=\"data row3 col0\" >Best Checkpoint Epoch</td>\n",
              "      <td id=\"T_0ad47_row3_col1\" class=\"data row3 col1\" >23</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row4_col0\" class=\"data row4 col0\" >Training Accuracy at Best Epoch</td>\n",
              "      <td id=\"T_0ad47_row4_col1\" class=\"data row4 col1\" >89.56%</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row5_col0\" class=\"data row5 col0\" >Validation Accuracy at Best Epoch</td>\n",
              "      <td id=\"T_0ad47_row5_col1\" class=\"data row5 col1\" >88.62%</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row6_col0\" class=\"data row6 col0\" >Training Loss at Best Epoch</td>\n",
              "      <td id=\"T_0ad47_row6_col1\" class=\"data row6 col1\" >0.3083</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row7_col0\" class=\"data row7 col0\" >Best Validation Loss</td>\n",
              "      <td id=\"T_0ad47_row7_col1\" class=\"data row7 col1\" >0.3071</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row8_col0\" class=\"data row8 col0\" >Highest Validation Accuracy</td>\n",
              "      <td id=\"T_0ad47_row8_col1\" class=\"data row8 col1\" >89.64%</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row9_col0\" class=\"data row9 col0\" >Highest Validation Accuracy Epoch</td>\n",
              "      <td id=\"T_0ad47_row9_col1\" class=\"data row9 col1\" >28</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_0ad47_row10_col0\" class=\"data row10 col0\" >Best Checkpoint Saved</td>\n",
              "      <td id=\"T_0ad47_row10_col1\" class=\"data row10 col1\" >Yes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 12. Training and Validation Curves"
      ],
      "metadata": {
        "id": "jaVXmrCwgw9v"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "\n",
        "epochs = range(\n",
        "    1,\n",
        "    len(history_experiment6.history[\"accuracy\"]) + 1\n",
        ")\n",
        "\n",
        "best_epoch = int(\n",
        "    np.argmin(history_experiment6.history[\"val_loss\"]) + 1\n",
        ")\n",
        "\n",
        "plt.figure(figsize=(12, 5))\n",
        "\n",
        "# Accuracy graph\n",
        "plt.subplot(1, 2, 1)\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment6.history[\"accuracy\"],\n",
        "    label=\"Training Accuracy\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment6.history[\"val_accuracy\"],\n",
        "    label=\"Validation Accuracy\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.axvline(\n",
        "    best_epoch,\n",
        "    linestyle=\"--\",\n",
        "    label=f\"Best Epoch ({best_epoch})\"\n",
        ")\n",
        "\n",
        "plt.title(\"Experiment 6 CNN Accuracy\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Accuracy\")\n",
        "plt.xticks(epochs)\n",
        "plt.legend()\n",
        "plt.grid(alpha=0.3)\n",
        "\n",
        "# Loss graph\n",
        "plt.subplot(1, 2, 2)\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment6.history[\"loss\"],\n",
        "    label=\"Training Loss\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment6.history[\"val_loss\"],\n",
        "    label=\"Validation Loss\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.axvline(\n",
        "    best_epoch,\n",
        "    linestyle=\"--\",\n",
        "    label=f\"Best Epoch ({best_epoch})\"\n",
        ")\n",
        "\n",
        "plt.title(\"Experiment 6 CNN Loss\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Loss\")\n",
        "plt.xticks(epochs)\n",
        "plt.legend()\n",
        "plt.grid(alpha=0.3)\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 507
        },
        "id": "XAX2KmjuNoNE",
        "outputId": "79971175-74b3-4bea-d06c-811ca5c957de"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}