{
 "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",
   "metadata": {},
   "source": [
    "## 1. Mount Google Drive\n",
    "\n",
    "Google Drive is connected to access the dataset and save the final trained model.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "from google.colab import drive\n",
    "drive.mount('/content/drive')"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "U7UVgM_Ou476",
    "outputId": "1c78a47b-ff51-4793-d604-41008e75e782"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Mounted at /content/drive\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Verify the Dataset File\n",
    "\n",
    "This check confirms that the compressed Plant Pathology dataset is available in Google Drive.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "J3g07eDFqzmY",
    "outputId": "76ac8ef9-ce1d-4d78-8844-3b637a9656a6"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "True\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "print(os.path.exists(\"/content/drive/MyDrive/PlantPathology_Split.zip\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Extract the Dataset\n",
    "\n",
    "The dataset archive is extracted into the Colab working directory.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "!unzip -q \"/content/drive/MyDrive/PlantPathology_Split.zip\" -d \"/content/\""
   ],
   "metadata": {
    "id": "HDCNqa4xwaq5"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Inspect the Extracted Folder\n",
    "\n",
    "The extracted directory is checked before the images are loaded into the pipeline.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "!ls \"/content/PlantPathology_Split\""
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "241jCc1XyfV6",
    "outputId": "0d299b3f-e7e1-4c34-981d-bc692752b741"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "test  train  valid\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 5. Import Libraries and Load the Image Data\n",
    "\n",
    "The required libraries and image settings are defined, then the training, validation and test datasets are loaded.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Load libraries\n",
    "import os\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras import layers, models\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Image settings\n",
    "IMG_SIZE = (512, 512)\n",
    "BATCH_SIZE = 32\n",
    "\n",
    "# Required five classes\n",
    "selected_classes = [\n",
    "    \"frog_eye_leaf_spot\",\n",
    "    \"healthy\",\n",
    "    \"powdery_mildew\",\n",
    "    \"rust\",\n",
    "    \"scab\"\n",
    "]\n",
    "\n",
    "train_ds = tf.keras.utils.image_dataset_from_directory(\n",
    "    \"/content/PlantPathology_Split/train\",\n",
    "    class_names=selected_classes,\n",
    "    image_size=IMG_SIZE,\n",
    "    batch_size=BATCH_SIZE,\n",
    "    label_mode=\"int\"\n",
    ")\n",
    "\n",
    "valid_ds = tf.keras.utils.image_dataset_from_directory(\n",
    "    \"/content/PlantPathology_Split/valid\",\n",
    "    class_names=selected_classes,\n",
    "    image_size=IMG_SIZE,\n",
    "    batch_size=BATCH_SIZE,\n",
    "    label_mode=\"int\"\n",
    ")\n",
    "\n",
    "test_ds = tf.keras.utils.image_dataset_from_directory(\n",
    "    \"/content/PlantPathology_Split/test\",\n",
    "    class_names=selected_classes,\n",
    "    image_size=IMG_SIZE,\n",
    "    batch_size=BATCH_SIZE,\n",
    "    label_mode=\"int\",\n",
    "    shuffle=False\n",
    ")\n",
    "\n",
    "# Display selected classes\n",
    "class_names = train_ds.class_names\n",
    "\n",
    "print(\"Classes:\")\n",
    "print(class_names)"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "MFt4tEfiynlQ",
    "outputId": "a00d4029-3d88-4fe9-c0b7-eee076d3c509"
   },
   "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",
      "Classes:\n",
      "['frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 6. Optimise the Data Pipeline\n",
    "\n",
    "Prefetching prepares image batches in advance and improves training efficiency.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "AUTOTUNE = tf.data.AUTOTUNE\n",
    "\n",
    "train_ds = train_ds.prefetch(AUTOTUNE)\n",
    "valid_ds = valid_ds.prefetch(AUTOTUNE)\n",
    "test_ds = test_ds.prefetch(AUTOTUNE)"
   ],
   "metadata": {
    "id": "T28L_smdztQU"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 7. Build the Final CNN Architecture\n",
    "\n",
    "The final model combines data augmentation, convolutional blocks, regularisation and a softmax output layer.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Data augmentation\n",
    "data_augmentation_tuned = models.Sequential([\n",
    "    layers.RandomFlip(\"horizontal\"),\n",
    "    layers.RandomRotation(0.1),\n",
    "    layers.RandomZoom(0.1)\n",
    "])\n",
    "\n",
    "# Build the Tuned Deeper CNN model\n",
    "num_classes = len(class_names)\n",
    "\n",
    "tuned_deeper_cnn_model = models.Sequential([\n",
    "    layers.Rescaling(1./255, input_shape=(512, 512, 3)),\n",
    "\n",
    "    data_augmentation_tuned,\n",
    "\n",
    "    # Larger kernel in the first convolutional layer\n",
    "    layers.Conv2D(32, 5, 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",
    "    # Additional convolutional block\n",
    "    layers.Conv2D(256, 3, activation='relu'),\n",
    "    layers.MaxPooling2D(),\n",
    "\n",
    "    layers.Flatten(),\n",
    "\n",
    "    layers.Dense(128, activation='relu'),\n",
    "    layers.Dropout(0.4),\n",
    "\n",
    "    layers.Dense(num_classes, activation='softmax')\n",
    "])\n",
    "\n",
    "tuned_deeper_cnn_model.summary()"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 633
    },
    "id": "m-SN90ngz6xW",
    "outputId": "bf0afa27-ff47-41fa-cc53-99488bf4dc70"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stderr",
     "text": [
      "/usr/local/lib/python3.12/dist-packages/keras/src/layers/preprocessing/data_layer.py:95: 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__(**kwargs)\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1mModel: \"sequential_4\"\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_4\"</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",
       "│ rescaling_1 (\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",
       "│ sequential_3 (\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",
       "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m508\u001b[0m, \u001b[38;5;34m508\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │         \u001b[38;5;34m2,432\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m252\u001b[0m, \u001b[38;5;34m252\u001b[0m, \u001b[38;5;34m64\u001b[0m)   │        \u001b[38;5;34m18,496\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_4 (\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_5 (\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_5 (\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_6 (\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_6 (\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_2 (\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_1 (\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_3 (\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",
       "│ rescaling_1 (<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",
       "│ sequential_3 (<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",
       "│ 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\">508</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">508</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,432</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\">254</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">254</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_4 (<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\">252</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">252</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_4 (<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_5 (<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_5 (<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_6 (<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_6 (<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_2 (<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_1 (<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_3 (<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;34m29,881,925\u001b[0m (113.99 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\">29,881,925</span> (113.99 MB)\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m29,881,925\u001b[0m (113.99 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\">29,881,925</span> (113.99 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",
   "metadata": {},
   "source": [
    "## 8. Compile the Final CNN Model\n",
    "\n",
    "The model is configured with the Adam optimiser, sparse categorical cross-entropy and accuracy.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Compile the Tuned Deeper CNN model\n",
    "tuned_deeper_cnn_model.compile(\n",
    "    optimizer=tf.keras.optimizers.Adam(\n",
    "        learning_rate=0.0002\n",
    "    ),\n",
    "    loss='sparse_categorical_crossentropy',\n",
    "    metrics=['accuracy']\n",
    ")"
   ],
   "metadata": {
    "id": "syzhnwu-z8Sv"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 9. Save the Best Model\n",
    "\n",
    "ModelCheckpoint stores the version with the lowest validation loss during training.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Save the best model silently\n",
    "checkpoint_tuned = tf.keras.callbacks.ModelCheckpoint(\n",
    "    \"/content/drive/MyDrive/tuned_deeper_cnn_best.keras\",\n",
    "    monitor='val_loss',\n",
    "    save_best_only=True,\n",
    "    verbose=0\n",
    ")"
   ],
   "metadata": {
    "id": "d-9ZBs5xrEDp"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 10. Configure Early Stopping\n",
    "\n",
    "Training stops when validation loss no longer improves and the best weights are restored.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Stop training after 8 epochs without improvement\n",
    "early_stopping_tuned = tf.keras.callbacks.EarlyStopping(\n",
    "    monitor='val_loss',\n",
    "    patience=8,\n",
    "    restore_best_weights=True,\n",
    "    verbose=0\n",
    ")"
   ],
   "metadata": {
    "id": "i9zcvYUn71Ma"
   },
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 11. Train the Final CNN Model\n",
    "\n",
    "The model is trained for up to 40 epochs using the validation set and selected callbacks.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Train the Tuned Deeper CNN model\n",
    "history_tuned_deeper = tuned_deeper_cnn_model.fit(\n",
    "    train_ds,\n",
    "    validation_data=valid_ds,\n",
    "    epochs=40,\n",
    "    callbacks=[\n",
    "        early_stopping_tuned,\n",
    "        checkpoint_tuned\n",
    "    ]\n",
    ")"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "l9YL4e4f0ZWI",
    "outputId": "b006d98c-c000-4da3-820a-eda71c405635"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Epoch 1/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m84s\u001b[0m 338ms/step - accuracy: 0.3848 - loss: 1.3867 - val_accuracy: 0.4815 - val_loss: 1.2533\n",
      "Epoch 2/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 326ms/step - accuracy: 0.5124 - loss: 1.1765 - val_accuracy: 0.5288 - val_loss: 1.1161\n",
      "Epoch 3/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 347ms/step - accuracy: 0.5922 - loss: 1.0288 - val_accuracy: 0.6554 - val_loss: 0.9084\n",
      "Epoch 4/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 326ms/step - accuracy: 0.6517 - loss: 0.8818 - val_accuracy: 0.6477 - val_loss: 0.8650\n",
      "Epoch 5/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 319ms/step - accuracy: 0.6843 - loss: 0.7990 - val_accuracy: 0.7097 - val_loss: 0.7057\n",
      "Epoch 6/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 319ms/step - accuracy: 0.7103 - loss: 0.7334 - val_accuracy: 0.7161 - val_loss: 0.7056\n",
      "Epoch 7/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 319ms/step - accuracy: 0.7210 - loss: 0.7010 - val_accuracy: 0.7430 - val_loss: 0.6578\n",
      "Epoch 8/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 319ms/step - accuracy: 0.7333 - loss: 0.6739 - val_accuracy: 0.7391 - val_loss: 0.6208\n",
      "Epoch 9/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m84s\u001b[0m 326ms/step - accuracy: 0.7448 - loss: 0.6355 - val_accuracy: 0.7481 - val_loss: 0.6147\n",
      "Epoch 10/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 325ms/step - accuracy: 0.7702 - loss: 0.5970 - val_accuracy: 0.7769 - val_loss: 0.5871\n",
      "Epoch 11/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 310ms/step - accuracy: 0.7731 - loss: 0.5853 - val_accuracy: 0.7685 - val_loss: 0.5954\n",
      "Epoch 12/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m86s\u001b[0m 330ms/step - accuracy: 0.7903 - loss: 0.5471 - val_accuracy: 0.8069 - val_loss: 0.5028\n",
      "Epoch 13/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 314ms/step - accuracy: 0.8143 - loss: 0.4941 - val_accuracy: 0.8114 - val_loss: 0.5249\n",
      "Epoch 14/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 323ms/step - accuracy: 0.8224 - loss: 0.4813 - val_accuracy: 0.8350 - val_loss: 0.4508\n",
      "Epoch 15/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m83s\u001b[0m 326ms/step - accuracy: 0.8354 - loss: 0.4381 - val_accuracy: 0.8382 - val_loss: 0.4250\n",
      "Epoch 16/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 313ms/step - accuracy: 0.8473 - loss: 0.4236 - val_accuracy: 0.8331 - val_loss: 0.4488\n",
      "Epoch 17/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 323ms/step - accuracy: 0.8625 - loss: 0.3861 - val_accuracy: 0.8574 - val_loss: 0.4162\n",
      "Epoch 18/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 321ms/step - accuracy: 0.8615 - loss: 0.3912 - val_accuracy: 0.8702 - val_loss: 0.3824\n",
      "Epoch 19/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 326ms/step - accuracy: 0.8663 - loss: 0.3745 - val_accuracy: 0.8619 - val_loss: 0.3703\n",
      "Epoch 20/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 320ms/step - accuracy: 0.8867 - loss: 0.3257 - val_accuracy: 0.8862 - val_loss: 0.3356\n",
      "Epoch 21/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 311ms/step - accuracy: 0.8935 - loss: 0.3196 - val_accuracy: 0.8875 - val_loss: 0.3509\n",
      "Epoch 22/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 311ms/step - accuracy: 0.8913 - loss: 0.3077 - val_accuracy: 0.8785 - val_loss: 0.3463\n",
      "Epoch 23/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 323ms/step - accuracy: 0.8945 - loss: 0.2922 - val_accuracy: 0.8945 - val_loss: 0.2900\n",
      "Epoch 24/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 314ms/step - accuracy: 0.9047 - loss: 0.2817 - val_accuracy: 0.8798 - val_loss: 0.3693\n",
      "Epoch 25/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 313ms/step - accuracy: 0.9056 - loss: 0.2823 - val_accuracy: 0.9035 - val_loss: 0.3060\n",
      "Epoch 26/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 324ms/step - accuracy: 0.9008 - loss: 0.2812 - val_accuracy: 0.9066 - val_loss: 0.2788\n",
      "Epoch 27/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 324ms/step - accuracy: 0.9164 - loss: 0.2492 - val_accuracy: 0.9073 - val_loss: 0.2785\n",
      "Epoch 28/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 317ms/step - accuracy: 0.9153 - loss: 0.2530 - val_accuracy: 0.9073 - val_loss: 0.2825\n",
      "Epoch 29/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 317ms/step - accuracy: 0.9124 - loss: 0.2587 - val_accuracy: 0.9060 - val_loss: 0.2976\n",
      "Epoch 30/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 313ms/step - accuracy: 0.9256 - loss: 0.2190 - val_accuracy: 0.9028 - val_loss: 0.3808\n",
      "Epoch 31/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m83s\u001b[0m 318ms/step - accuracy: 0.9230 - loss: 0.2284 - val_accuracy: 0.8971 - val_loss: 0.3072\n",
      "Epoch 32/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 310ms/step - accuracy: 0.9291 - loss: 0.2032 - val_accuracy: 0.9022 - val_loss: 0.2867\n",
      "Epoch 33/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m85s\u001b[0m 322ms/step - accuracy: 0.9305 - loss: 0.2183 - val_accuracy: 0.9130 - val_loss: 0.2747\n",
      "Epoch 34/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 321ms/step - accuracy: 0.9284 - loss: 0.2134 - val_accuracy: 0.9239 - val_loss: 0.2332\n",
      "Epoch 35/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 318ms/step - accuracy: 0.9335 - loss: 0.1955 - val_accuracy: 0.9092 - val_loss: 0.3059\n",
      "Epoch 36/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 325ms/step - accuracy: 0.9292 - loss: 0.2178 - val_accuracy: 0.9284 - val_loss: 0.2271\n",
      "Epoch 37/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 316ms/step - accuracy: 0.9369 - loss: 0.1883 - val_accuracy: 0.9182 - val_loss: 0.2597\n",
      "Epoch 38/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 312ms/step - accuracy: 0.9394 - loss: 0.1844 - val_accuracy: 0.9220 - val_loss: 0.2560\n",
      "Epoch 39/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 324ms/step - accuracy: 0.9414 - loss: 0.1703 - val_accuracy: 0.9335 - val_loss: 0.2111\n",
      "Epoch 40/40\n",
      "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 314ms/step - accuracy: 0.9484 - loss: 0.1527 - val_accuracy: 0.9188 - val_loss: 0.2877\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 12. Visualise Training Performance\n",
    "\n",
    "Accuracy and loss curves are compared to assess learning progress and possible overfitting.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Plot training and validation results\n",
    "plt.figure(figsize=(12, 5))\n",
    "\n",
    "# Accuracy\n",
    "plt.subplot(1, 2, 1)\n",
    "\n",
    "plt.plot(\n",
    "    history_tuned_deeper.history['accuracy'],\n",
    "    color='lightskyblue'\n",
    ")\n",
    "\n",
    "plt.plot(\n",
    "    history_tuned_deeper.history['val_accuracy'],\n",
    "    color='lightgreen'\n",
    ")\n",
    "\n",
    "plt.title('Tuned Deeper CNN Accuracy')\n",
    "plt.xlabel('Epoch')\n",
    "plt.ylabel('Accuracy')\n",
    "plt.legend(['Training', 'Validation'])\n",
    "\n",
    "# Loss\n",
    "plt.subplot(1, 2, 2)\n",
    "\n",
    "plt.plot(\n",
    "    history_tuned_deeper.history['loss'],\n",
    "    color='lightskyblue'\n",
    ")\n",
    "\n",
    "plt.plot(\n",
    "    history_tuned_deeper.history['val_loss'],\n",
    "    color='lightgreen'\n",
    ")\n",
    "\n",
    "plt.title('Tuned Deeper CNN Loss')\n",
    "plt.xlabel('Epoch')\n",
    "plt.ylabel('Loss')\n",
    "plt.legend(['Training', 'Validation'])\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 388
    },
    "id": "7FmxqaGeLUbY",
    "outputId": "eeb236a8-adcd-46d8-cd36-f36d0db7140a"
   },
   "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": {}
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 13. Create the Epoch Results Table\n",
    "\n",
    "Training and validation metrics are organised into a table for clearer comparison.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "import pandas as pd\n",
    "\n",
    "tuned_deeper_results = pd.DataFrame({\n",
    "    'Epoch': range(\n",
    "        1,\n",
    "        len(history_tuned_deeper.history['accuracy']) + 1\n",
    "    ),\n",
    "    'Training Accuracy':\n",
    "        history_tuned_deeper.history['accuracy'],\n",
    "    'Validation Accuracy':\n",
    "        history_tuned_deeper.history['val_accuracy'],\n",
    "    'Training Loss':\n",
    "        history_tuned_deeper.history['loss'],\n",
    "    'Validation Loss':\n",
    "        history_tuned_deeper.history['val_loss']\n",
    "})\n",
    "\n",
    "tuned_deeper_results.round(4)"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "zLG9Df2j3cp3",
    "outputId": "ad5d6189-a03d-4cda-c98a-6d3ce43ec501"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "    Epoch  Training Accuracy  Validation Accuracy  Training Loss  \\\n",
       "0       1             0.3848               0.4815         1.3867   \n",
       "1       2             0.5124               0.5288         1.1765   \n",
       "2       3             0.5922               0.6554         1.0288   \n",
       "3       4             0.6517               0.6477         0.8818   \n",
       "4       5             0.6843               0.7097         0.7990   \n",
       "5       6             0.7103               0.7161         0.7334   \n",
       "6       7             0.7210               0.7430         0.7010   \n",
       "7       8             0.7333               0.7391         0.6739   \n",
       "8       9             0.7448               0.7481         0.6355   \n",
       "9      10             0.7702               0.7769         0.5970   \n",
       "10     11             0.7731               0.7685         0.5853   \n",
       "11     12             0.7903               0.8069         0.5471   \n",
       "12     13             0.8143               0.8114         0.4941   \n",
       "13     14             0.8224               0.8350         0.4813   \n",
       "14     15             0.8354               0.8382         0.4381   \n",
       "15     16             0.8473               0.8331         0.4236   \n",
       "16     17             0.8625               0.8574         0.3861   \n",
       "17     18             0.8615               0.8702         0.3912   \n",
       "18     19             0.8663               0.8619         0.3745   \n",
       "19     20             0.8867               0.8862         0.3257   \n",
       "20     21             0.8935               0.8875         0.3196   \n",
       "21     22             0.8913               0.8785         0.3077   \n",
       "22     23             0.8945               0.8945         0.2922   \n",
       "23     24             0.9047               0.8798         0.2817   \n",
       "24     25             0.9056               0.9035         0.2823   \n",
       "25     26             0.9008               0.9066         0.2812   \n",
       "26     27             0.9164               0.9073         0.2492   \n",
       "27     28             0.9153               0.9073         0.2530   \n",
       "28     29             0.9124               0.9060         0.2587   \n",
       "29     30             0.9256               0.9028         0.2190   \n",
       "30     31             0.9230               0.8971         0.2284   \n",
       "31     32             0.9291               0.9022         0.2032   \n",
       "32     33             0.9305               0.9130         0.2183   \n",
       "33     34             0.9284               0.9239         0.2134   \n",
       "34     35             0.9335               0.9092         0.1955   \n",
       "35     36             0.9292               0.9284         0.2178   \n",
       "36     37             0.9369               0.9182         0.1883   \n",
       "37     38             0.9394               0.9220         0.1844   \n",
       "38     39             0.9414               0.9335         0.1703   \n",
       "39     40             0.9484               0.9188         0.1527   \n",
       "\n",
       "    Validation Loss  \n",
       "0            1.2533  \n",
       "1            1.1161  \n",
       "2            0.9084  \n",
       "3            0.8650  \n",
       "4            0.7057  \n",
       "5            0.7056  \n",
       "6            0.6578  \n",
       "7            0.6208  \n",
       "8            0.6147  \n",
       "9            0.5871  \n",
       "10           0.5954  \n",
       "11           0.5028  \n",
       "12           0.5249  \n",
       "13           0.4508  \n",
       "14           0.4250  \n",
       "15           0.4488  \n",
       "16           0.4162  \n",
       "17           0.3824  \n",
       "18           0.3703  \n",
       "19           0.3356  \n",
       "20           0.3509  \n",
       "21           0.3463  \n",
       "22           0.2900  \n",
       "23           0.3693  \n",
       "24           0.3060  \n",
       "25           0.2788  \n",
       "26           0.2785  \n",
       "27           0.2825  \n",
       "28           0.2976  \n",
       "29           0.3808  \n",
       "30           0.3072  \n",
       "31           0.2867  \n",
       "32           0.2747  \n",
       "33           0.2332  \n",
       "34           0.3059  \n",
       "35           0.2271  \n",
       "36           0.2597  \n",
       "37           0.2560  \n",
       "38           0.2111  \n",
       "39           0.2877  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-d6fd0bbb-ef6f-4eea-abcf-3bf9ee7a7974\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Epoch</th>\n",
       "      <th>Training Accuracy</th>\n",
       "      <th>Validation Accuracy</th>\n",
       "      <th>Training Loss</th>\n",
       "      <th>Validation Loss</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.3848</td>\n",
       "      <td>0.4815</td>\n",
       "      <td>1.3867</td>\n",
       "      <td>1.2533</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>0.5124</td>\n",
       "      <td>0.5288</td>\n",
       "      <td>1.1765</td>\n",
       "      <td>1.1161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>0.5922</td>\n",
       "      <td>0.6554</td>\n",
       "      <td>1.0288</td>\n",
       "      <td>0.9084</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>0.6517</td>\n",
       "      <td>0.6477</td>\n",
       "      <td>0.8818</td>\n",
       "      <td>0.8650</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0.6843</td>\n",
       "      <td>0.7097</td>\n",
       "      <td>0.7990</td>\n",
       "      <td>0.7057</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>0.7103</td>\n",
       "      <td>0.7161</td>\n",
       "      <td>0.7334</td>\n",
       "      <td>0.7056</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>0.7210</td>\n",
       "      <td>0.7430</td>\n",
       "      <td>0.7010</td>\n",
       "      <td>0.6578</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>0.7333</td>\n",
       "      <td>0.7391</td>\n",
       "      <td>0.6739</td>\n",
       "      <td>0.6208</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>0.7448</td>\n",
       "      <td>0.7481</td>\n",
       "      <td>0.6355</td>\n",
       "      <td>0.6147</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>0.7702</td>\n",
       "      <td>0.7769</td>\n",
       "      <td>0.5970</td>\n",
       "      <td>0.5871</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11</td>\n",
       "      <td>0.7731</td>\n",
       "      <td>0.7685</td>\n",
       "      <td>0.5853</td>\n",
       "      <td>0.5954</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12</td>\n",
       "      <td>0.7903</td>\n",
       "      <td>0.8069</td>\n",
       "      <td>0.5471</td>\n",
       "      <td>0.5028</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>13</td>\n",
       "      <td>0.8143</td>\n",
       "      <td>0.8114</td>\n",
       "      <td>0.4941</td>\n",
       "      <td>0.5249</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>14</td>\n",
       "      <td>0.8224</td>\n",
       "      <td>0.8350</td>\n",
       "      <td>0.4813</td>\n",
       "      <td>0.4508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>15</td>\n",
       "      <td>0.8354</td>\n",
       "      <td>0.8382</td>\n",
       "      <td>0.4381</td>\n",
       "      <td>0.4250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>16</td>\n",
       "      <td>0.8473</td>\n",
       "      <td>0.8331</td>\n",
       "      <td>0.4236</td>\n",
       "      <td>0.4488</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>17</td>\n",
       "      <td>0.8625</td>\n",
       "      <td>0.8574</td>\n",
       "      <td>0.3861</td>\n",
       "      <td>0.4162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>18</td>\n",
       "      <td>0.8615</td>\n",
       "      <td>0.8702</td>\n",
       "      <td>0.3912</td>\n",
       "      <td>0.3824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>19</td>\n",
       "      <td>0.8663</td>\n",
       "      <td>0.8619</td>\n",
       "      <td>0.3745</td>\n",
       "      <td>0.3703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20</td>\n",
       "      <td>0.8867</td>\n",
       "      <td>0.8862</td>\n",
       "      <td>0.3257</td>\n",
       "      <td>0.3356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>21</td>\n",
       "      <td>0.8935</td>\n",
       "      <td>0.8875</td>\n",
       "      <td>0.3196</td>\n",
       "      <td>0.3509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>22</td>\n",
       "      <td>0.8913</td>\n",
       "      <td>0.8785</td>\n",
       "      <td>0.3077</td>\n",
       "      <td>0.3463</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>23</td>\n",
       "      <td>0.8945</td>\n",
       "      <td>0.8945</td>\n",
       "      <td>0.2922</td>\n",
       "      <td>0.2900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>24</td>\n",
       "      <td>0.9047</td>\n",
       "      <td>0.8798</td>\n",
       "      <td>0.2817</td>\n",
       "      <td>0.3693</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>25</td>\n",
       "      <td>0.9056</td>\n",
       "      <td>0.9035</td>\n",
       "      <td>0.2823</td>\n",
       "      <td>0.3060</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>26</td>\n",
       "      <td>0.9008</td>\n",
       "      <td>0.9066</td>\n",
       "      <td>0.2812</td>\n",
       "      <td>0.2788</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>27</td>\n",
       "      <td>0.9164</td>\n",
       "      <td>0.9073</td>\n",
       "      <td>0.2492</td>\n",
       "      <td>0.2785</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>28</td>\n",
       "      <td>0.9153</td>\n",
       "      <td>0.9073</td>\n",
       "      <td>0.2530</td>\n",
       "      <td>0.2825</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>29</td>\n",
       "      <td>0.9124</td>\n",
       "      <td>0.9060</td>\n",
       "      <td>0.2587</td>\n",
       "      <td>0.2976</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>30</td>\n",
       "      <td>0.9256</td>\n",
       "      <td>0.9028</td>\n",
       "      <td>0.2190</td>\n",
       "      <td>0.3808</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>31</td>\n",
       "      <td>0.9230</td>\n",
       "      <td>0.8971</td>\n",
       "      <td>0.2284</td>\n",
       "      <td>0.3072</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>32</td>\n",
       "      <td>0.9291</td>\n",
       "      <td>0.9022</td>\n",
       "      <td>0.2032</td>\n",
       "      <td>0.2867</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>33</td>\n",
       "      <td>0.9305</td>\n",
       "      <td>0.9130</td>\n",
       "      <td>0.2183</td>\n",
       "      <td>0.2747</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>34</td>\n",
       "      <td>0.9284</td>\n",
       "      <td>0.9239</td>\n",
       "      <td>0.2134</td>\n",
       "      <td>0.2332</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>35</td>\n",
       "      <td>0.9335</td>\n",
       "      <td>0.9092</td>\n",
       "      <td>0.1955</td>\n",
       "      <td>0.3059</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>36</td>\n",
       "      <td>0.9292</td>\n",
       "      <td>0.9284</td>\n",
       "      <td>0.2178</td>\n",
       "      <td>0.2271</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>37</td>\n",
       "      <td>0.9369</td>\n",
       "      <td>0.9182</td>\n",
       "      <td>0.1883</td>\n",
       "      <td>0.2597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>38</td>\n",
       "      <td>0.9394</td>\n",
       "      <td>0.9220</td>\n",
       "      <td>0.1844</td>\n",
       "      <td>0.2560</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>39</td>\n",
       "      <td>0.9414</td>\n",
       "      <td>0.9335</td>\n",
       "      <td>0.1703</td>\n",
       "      <td>0.2111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>40</td>\n",
       "      <td>0.9484</td>\n",
       "      <td>0.9188</td>\n",
       "      <td>0.1527</td>\n",
       "      <td>0.2877</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d6fd0bbb-ef6f-4eea-abcf-3bf9ee7a7974')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-d6fd0bbb-ef6f-4eea-abcf-3bf9ee7a7974 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-d6fd0bbb-ef6f-4eea-abcf-3bf9ee7a7974');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"tuned_deeper_results\",\n  \"rows\": 40,\n  \"fields\": [\n    {\n      \"column\": \"Epoch\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 11,\n        \"min\": 1,\n        \"max\": 40,\n        \"num_unique_values\": 40,\n        \"samples\": [\n          20,\n          17,\n          16\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Training Accuracy\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.12755263948560058,\n        \"min\": 0.3848,\n        \"max\": 0.9484,\n        \"num_unique_values\": 40,\n        \"samples\": [\n          0.8867,\n          0.8625,\n          0.8473\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Validation Accuracy\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.10892710147569996,\n        \"min\": 0.4815,\n        \"max\": 0.9335,\n        \"num_unique_values\": 39,\n        \"samples\": [\n          0.9092,\n          0.922,\n          0.7097\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Training Loss\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.29163945750374204,\n        \"min\": 0.1527,\n        \"max\": 1.3867,\n        \"num_unique_values\": 40,\n        \"samples\": [\n          0.3257,\n          0.3861,\n          0.4236\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Validation Loss\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.24357676396222133,\n        \"min\": 0.2111,\n        \"max\": 1.2533,\n        \"num_unique_values\": 40,\n        \"samples\": [\n          0.3356,\n          0.4162,\n          0.4488\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 28
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 14. Identify the Best Epoch\n",
    "\n",
    "The best epoch is selected using the lowest recorded validation loss.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Find the best epoch based on the lowest validation loss\n",
    "best_tuned_epoch = tuned_deeper_results.loc[\n",
    "    tuned_deeper_results['Validation Loss'].idxmin()\n",
    "]\n",
    "\n",
    "best_tuned_summary = pd.DataFrame({\n",
    "    'Metric': [\n",
    "        'Best Epoch',\n",
    "        'Training Accuracy',\n",
    "        'Validation Accuracy',\n",
    "        'Training Loss',\n",
    "        'Validation Loss'\n",
    "    ],\n",
    "    'Result': [\n",
    "        int(best_tuned_epoch['Epoch']),\n",
    "        f\"{best_tuned_epoch['Training Accuracy'] * 100:.2f}%\",\n",
    "        f\"{best_tuned_epoch['Validation Accuracy'] * 100:.2f}%\",\n",
    "        f\"{best_tuned_epoch['Training Loss']:.4f}\",\n",
    "        f\"{best_tuned_epoch['Validation Loss']:.4f}\"\n",
    "    ]\n",
    "})\n",
    "\n",
    "best_tuned_summary.style\\\n",
    "    .hide(axis='index')\\\n",
    "    .set_caption(\"Best Tuned Deeper CNN Results\")\\\n",
    "    .set_properties(**{\n",
    "        'text-align': 'center',\n",
    "        'padding': '8px'\n",
    "    })\\\n",
    "    .set_table_styles([\n",
    "        {\n",
    "            'selector': 'caption',\n",
    "            'props': [\n",
    "                ('font-size', '17px'),\n",
    "                ('font-weight', 'bold'),\n",
    "                ('padding', '10px')\n",
    "            ]\n",
    "        },\n",
    "        {\n",
    "            'selector': 'th',\n",
    "            'props': [\n",
    "                ('font-weight', 'bold'),\n",
    "                ('text-align', 'center'),\n",
    "                ('border-bottom', '1px solid #999')\n",
    "            ]\n",
    "        },\n",
    "        {\n",
    "            'selector': 'tbody tr:nth-child(odd)',\n",
    "            'props': [\n",
    "                ('background-color', '#f2f2f2')\n",
    "            ]\n",
    "        },\n",
    "        {\n",
    "            'selector': 'tbody tr:nth-child(even)',\n",
    "            'props': [\n",
    "                ('background-color', '#ffffff')\n",
    "            ]\n",
    "        },\n",
    "        {\n",
    "            'selector': 'tbody td:first-child',\n",
    "            'props': [\n",
    "                ('font-weight', 'bold'),\n",
    "                ('text-align', 'left')\n",
    "            ]\n",
    "        }\n",
    "    ])"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 278
    },
    "id": "bQ1eBtqE4PXd",
    "outputId": "e8e86d3a-e4d8-45c3-8ce0-e99fad3a0f38"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7bbf777d9430>"
      ],
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_94298 caption {\n",
       "  font-size: 17px;\n",
       "  font-weight: bold;\n",
       "  padding: 10px;\n",
       "}\n",
       "#T_94298 th {\n",
       "  font-weight: bold;\n",
       "  text-align: center;\n",
       "  border-bottom: 1px solid #999;\n",
       "}\n",
       "#T_94298 tbody tr:nth-child(odd) {\n",
       "  background-color: #f2f2f2;\n",
       "}\n",
       "#T_94298 tbody tr:nth-child(even) {\n",
       "  background-color: #ffffff;\n",
       "}\n",
       "#T_94298 tbody td:first-child {\n",
       "  font-weight: bold;\n",
       "  text-align: left;\n",
       "}\n",
       "#T_94298_row0_col0, #T_94298_row0_col1, #T_94298_row1_col0, #T_94298_row1_col1, #T_94298_row2_col0, #T_94298_row2_col1, #T_94298_row3_col0, #T_94298_row3_col1, #T_94298_row4_col0, #T_94298_row4_col1 {\n",
       "  text-align: center;\n",
       "  padding: 8px;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_94298\" class=\"dataframe\">\n",
       "  <caption>Best Tuned Deeper CNN Results</caption>\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th id=\"T_94298_level0_col0\" class=\"col_heading level0 col0\" >Metric</th>\n",
       "      <th id=\"T_94298_level0_col1\" class=\"col_heading level0 col1\" >Result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td id=\"T_94298_row0_col0\" class=\"data row0 col0\" >Best Epoch</td>\n",
       "      <td id=\"T_94298_row0_col1\" class=\"data row0 col1\" >39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td id=\"T_94298_row1_col0\" class=\"data row1 col0\" >Training Accuracy</td>\n",
       "      <td id=\"T_94298_row1_col1\" class=\"data row1 col1\" >94.14%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td id=\"T_94298_row2_col0\" class=\"data row2 col0\" >Validation Accuracy</td>\n",
       "      <td id=\"T_94298_row2_col1\" class=\"data row2 col1\" >93.35%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td id=\"T_94298_row3_col0\" class=\"data row3 col0\" >Training Loss</td>\n",
       "      <td id=\"T_94298_row3_col1\" class=\"data row3 col1\" >0.1703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td id=\"T_94298_row4_col0\" class=\"data row4 col0\" >Validation Loss</td>\n",
       "      <td id=\"T_94298_row4_col1\" class=\"data row4 col1\" >0.2111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ]
     },
     "metadata": {},
     "execution_count": 31
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 15. Load the Best Saved Model\n",
    "\n",
    "The strongest saved model is loaded before the final evaluation.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "\n",
    "# 1. Încarcă modelul salvat\n",
    "model_path = \"/content/drive/MyDrive/tuned_deeper_cnn_best.keras\"\n",
    "\n",
    "best_model = tf.keras.models.load_model(model_path)\n",
    "\n",
    "print(\"Model loaded successfully.\")\n",
    "best_model.summary()"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 611
    },
    "id": "-n8dr3E4ART1",
    "outputId": "73bbe9af-b4c7-4659-bbf2-50ce93c821c7"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Model loaded successfully.\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1mModel: \"sequential_4\"\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_4\"</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",
       "│ rescaling_1 (\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",
       "│ sequential_3 (\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",
       "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m508\u001b[0m, \u001b[38;5;34m508\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │         \u001b[38;5;34m2,432\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m252\u001b[0m, \u001b[38;5;34m252\u001b[0m, \u001b[38;5;34m64\u001b[0m)   │        \u001b[38;5;34m18,496\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_4 (\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_5 (\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_5 (\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_6 (\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_6 (\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_2 (\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_1 (\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_3 (\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",
       "│ rescaling_1 (<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",
       "│ sequential_3 (<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",
       "│ 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\">508</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">508</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,432</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\">254</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">254</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_4 (<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\">252</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">252</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_4 (<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_5 (<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_5 (<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_6 (<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_6 (<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_2 (<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_1 (<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_3 (<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;34m89,645,777\u001b[0m (341.97 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\">89,645,777</span> (341.97 MB)\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m29,881,925\u001b[0m (113.99 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\">29,881,925</span> (113.99 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": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m59,763,852\u001b[0m (227.98 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\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">59,763,852</span> (227.98 MB)\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 16. Evaluate the Test Performance\n",
    "\n",
    "Test loss and test accuracy measure performance on images not used during training.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# 2. Evaluează modelul pe setul de test\n",
    "test_loss, test_accuracy = best_model.evaluate(test_ds, verbose=1)\n",
    "\n",
    "print(f\"Test Loss: {test_loss:.4f}\")\n",
    "print(f\"Test Accuracy: {test_accuracy:.4f}\")\n",
    "print(f\"Test Accuracy: {test_accuracy * 100:.2f}%\")"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "DgLuL2DJAfQV",
    "outputId": "144a1d65-23b6-404c-87c5-63fe906fc3dd"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m421s\u001b[0m 9s/step - accuracy: 0.9387 - loss: 0.1959\n",
      "Test Loss: 0.1959\n",
      "Test Accuracy: 0.9387\n",
      "Test Accuracy: 93.87%\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 17. Generate Predictions and Classification Metrics\n",
    "\n",
    "Predicted classes are compared with the true labels to produce detailed evaluation results.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# 3. Obține etichetele reale\n",
    "y_true = np.concatenate([\n",
    "    labels.numpy() for images, labels in test_ds\n",
    "])\n",
    "\n",
    "# 4. Obține predicțiile modelului\n",
    "y_prob = best_model.predict(test_ds, verbose=1)\n",
    "y_pred = np.argmax(y_prob, axis=1)\n",
    "\n",
    "# 5. Classification report\n",
    "print(classification_report(\n",
    "    y_true,\n",
    "    y_pred,\n",
    "    target_names=class_names,\n",
    "    digits=4\n",
    "))\n",
    "\n"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "TconzTDLBSlc",
    "outputId": "726ecada-bf75-4201-a376-01ba2428eaf2"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m392s\u001b[0m 8s/step\n",
      "                    precision    recall  f1-score   support\n",
      "\n",
      "frog_eye_leaf_spot     0.9522    0.9645    0.9583       310\n",
      "           healthy     0.9192    0.9461    0.9324       445\n",
      "    powdery_mildew     0.8623    0.9444    0.9015       126\n",
      "              rust     0.9719    0.9301    0.9505       186\n",
      "              scab     0.9582    0.9180    0.9377       500\n",
      "\n",
      "          accuracy                         0.9387      1567\n",
      "         macro avg     0.9328    0.9406    0.9361      1567\n",
      "      weighted avg     0.9399    0.9387    0.9389      1567\n",
      "\n",
      "Confusion Matrix:\n",
      "[[299   5   2   3   1]\n",
      " [  3 421   6   2  13]\n",
      " [  0   5 119   0   2]\n",
      " [  6   1   2 173   4]\n",
      " [  6  26   9   0 459]]\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 18. Display the Confusion Matrix\n",
    "\n",
    "The confusion matrix shows which plant disease classes were predicted correctly or confused.\n"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import ConfusionMatrixDisplay\n",
    "\n",
    "disp = ConfusionMatrixDisplay(\n",
    "    confusion_matrix=cm,\n",
    "    display_labels=class_names\n",
    ")\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(9, 7))\n",
    "disp.plot(\n",
    "    ax=ax,\n",
    "    cmap=\"Blues\",\n",
    "    values_format=\"d\",\n",
    "    xticks_rotation=45\n",
    ")\n",
    "\n",
    "plt.title(\"Confusion Matrix – Tuned Deeper CNN\")\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 707
    },
    "id": "YiLNmWskBWY_",
    "outputId": "fe285848-da22-4e07-8185-eb03982c8f91"
   },
   "execution_count": null,
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 900x700 with 2 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ]
  }
 ]
}