{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Facial Emotion Detection System"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Imports and Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Num GPUs Available:  0\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import cv2\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras.models import Sequential, load_model\n",
    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau, EarlyStopping\n",
    "from sklearn.model_selection import train_test_split\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "\n",
    "# Check GPU\n",
    "print(\"Num GPUs Available: \", len(tf.config.list_physical_devices('GPU')))\n",
    "try:\n",
    "    # Disable scientific notation for clarity\n",
    "    np.set_printoptions(suppress=True)\n",
    "except:\n",
    "    pass"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Data Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 2. Load Data from Organized Folders\n",
    "import os\n",
    "import cv2\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from tensorflow.keras.utils import to_categorical\n",
    "\n",
    "DATA_DIR = 'data/organized'\n",
    "EMOTIONS = ['Angry', 'Fear', 'Happy', 'Neutral', 'Sad', 'Surprise']\n",
    "class_map = {emotion: idx for idx, emotion in enumerate(EMOTIONS)}\n",
    "\n",
    "print('Loading images from directories...')\n",
    "images = []\n",
    "labels = []\n",
    "\n",
    "for emotion in EMOTIONS:\n",
    "    folder_path = os.path.join(DATA_DIR, emotion)\n",
    "    if not os.path.exists(folder_path):\n",
    "        print(f'Warning: Folder missing - {folder_path}')\n",
    "        continue\n",
    "        \n",
    "    label = class_map[emotion]\n",
    "    for img_name in os.listdir(folder_path):\n",
    "        img_path = os.path.join(folder_path, img_name)\n",
    "        img = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE)\n",
    "        if img is not None:\n",
    "            img = cv2.resize(img, (48, 48))\n",
    "            images.append(img)\n",
    "            labels.append(label)\n",
    "\n",
    "images = np.array(images, dtype='float32') / 255.0\n",
    "images_input = np.expand_dims(images, axis=-1)\n",
    "labels = np.array(labels)\n",
    "\n",
    "y_train_onehot_full = to_categorical(labels, num_classes=len(EMOTIONS))\n",
    "\n",
    "# Split into train/test\n",
    "X_train, X_test, y_train_onehot, y_test_onehot = train_test_split(\n",
    "    images_input, y_train_onehot_full, test_size=0.2, random_state=42, stratify=labels\n",
    ")\n",
    "\n",
    "print(f'Total images loaded: {len(images)}')\n",
    "print(f'Training set size: {X_train.shape[0]}')\n",
    "print(f'Validation set size: {X_test.shape[0]}')\n",
    "print(f'Input shape: {X_train.shape[1:]}')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Model Definition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\RUSL\\Third Year\\my\\ICT3212 - Introduction to Intelligent Systems\\Project\\Facial Emotion Detection System\\.venv\\Lib\\site-packages\\keras\\src\\layers\\convolutional\\base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    },
    {
     "data": {
      "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_1\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential_1\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\u250f\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2533\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2533\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2513\n",
       "\u2503<span style=\"font-weight: bold\"> Layer (type)                    </span>\u2503<span style=\"font-weight: bold\"> Output Shape           </span>\u2503<span style=\"font-weight: bold\">       Param # </span>\u2503\n",
       "\u2521\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2547\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2547\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2529\n",
       "\u2502 conv2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">48</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">48</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     \u2502           <span style=\"color: #00af00; text-decoration-color: #00af00\">640</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_6           \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">48</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">48</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     \u2502           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> \u2502\n",
       "\u2502 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 conv2d_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    \u2502       <span style=\"color: #00af00; text-decoration-color: #00af00\">204,928</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_7           \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    \u2502           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> \u2502\n",
       "\u2502 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 conv2d_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)    \u2502       <span style=\"color: #00af00; text-decoration-color: #00af00\">590,336</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_8           \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)    \u2502         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,048</span> \u2502\n",
       "\u2502 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 conv2d_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      \u2502     <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_9           \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      \u2502         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,048</span> \u2502\n",
       "\u2502 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 flatten_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)             \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4608</span>)           \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            \u2502     <span style=\"color: #00af00; text-decoration-color: #00af00\">1,179,904</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_10          \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            \u2502         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> \u2502\n",
       "\u2502 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dense_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            \u2502       <span style=\"color: #00af00; text-decoration-color: #00af00\">131,584</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_11          \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            \u2502         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,048</span> \u2502\n",
       "\u2502 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_11 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            \u2502             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dense_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 \u2502 (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>)              \u2502         <span style=\"color: #00af00; text-decoration-color: #00af00\">3,078</span> \u2502\n",
       "\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u250f\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2533\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2533\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2513\n",
       "\u2503\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m\u2503\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m\u2503\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m\u2503\n",
       "\u2521\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2547\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2547\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2529\n",
       "\u2502 conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m48\u001b[0m, \u001b[38;5;34m48\u001b[0m, \u001b[38;5;34m64\u001b[0m)     \u2502           \u001b[38;5;34m640\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_6           \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m48\u001b[0m, \u001b[38;5;34m48\u001b[0m, \u001b[38;5;34m64\u001b[0m)     \u2502           \u001b[38;5;34m256\u001b[0m \u2502\n",
       "\u2502 (\u001b[38;5;33mBatchNormalization\u001b[0m)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m64\u001b[0m)     \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_6 (\u001b[38;5;33mDropout\u001b[0m)             \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m64\u001b[0m)     \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m)               \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m128\u001b[0m)    \u2502       \u001b[38;5;34m204,928\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_7           \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m128\u001b[0m)    \u2502           \u001b[38;5;34m512\u001b[0m \u2502\n",
       "\u2502 (\u001b[38;5;33mBatchNormalization\u001b[0m)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_5 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m128\u001b[0m)    \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_7 (\u001b[38;5;33mDropout\u001b[0m)             \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m128\u001b[0m)    \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m)               \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m512\u001b[0m)    \u2502       \u001b[38;5;34m590,336\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_8           \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m512\u001b[0m)    \u2502         \u001b[38;5;34m2,048\u001b[0m \u2502\n",
       "\u2502 (\u001b[38;5;33mBatchNormalization\u001b[0m)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_6 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m512\u001b[0m)      \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_8 (\u001b[38;5;33mDropout\u001b[0m)             \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m512\u001b[0m)      \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m)               \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m512\u001b[0m)      \u2502     \u001b[38;5;34m2,359,808\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_9           \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m512\u001b[0m)      \u2502         \u001b[38;5;34m2,048\u001b[0m \u2502\n",
       "\u2502 (\u001b[38;5;33mBatchNormalization\u001b[0m)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 max_pooling2d_7 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m512\u001b[0m)      \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_9 (\u001b[38;5;33mDropout\u001b[0m)             \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m512\u001b[0m)      \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 flatten_1 (\u001b[38;5;33mFlatten\u001b[0m)             \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4608\u001b[0m)           \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dense_3 (\u001b[38;5;33mDense\u001b[0m)                 \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            \u2502     \u001b[38;5;34m1,179,904\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_10          \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            \u2502         \u001b[38;5;34m1,024\u001b[0m \u2502\n",
       "\u2502 (\u001b[38;5;33mBatchNormalization\u001b[0m)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_10 (\u001b[38;5;33mDropout\u001b[0m)            \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dense_4 (\u001b[38;5;33mDense\u001b[0m)                 \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            \u2502       \u001b[38;5;34m131,584\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 batch_normalization_11          \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            \u2502         \u001b[38;5;34m2,048\u001b[0m \u2502\n",
       "\u2502 (\u001b[38;5;33mBatchNormalization\u001b[0m)            \u2502                        \u2502               \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dropout_11 (\u001b[38;5;33mDropout\u001b[0m)            \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            \u2502             \u001b[38;5;34m0\u001b[0m \u2502\n",
       "\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n",
       "\u2502 dense_5 (\u001b[38;5;33mDense\u001b[0m)                 \u2502 (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m)              \u2502         \u001b[38;5;34m3,078\u001b[0m \u2502\n",
       "\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">4,478,214</span> (17.08 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,478,214\u001b[0m (17.08 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">4,474,246</span> (17.07 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m4,474,246\u001b[0m (17.07 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">3,968</span> (15.50 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m3,968\u001b[0m (15.50 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def build_model(input_shape=(48, 48, 1), num_classes=6):\n",
    "    model = Sequential()\n",
    "\n",
    "    # 1st Convolution Block\n",
    "    model.add(Conv2D(64, (3, 3), activation='relu', padding='same', input_shape=input_shape))\n",
    "    model.add(BatchNormalization())\n",
    "    model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "    model.add(Dropout(0.25))\n",
    "\n",
    "    # 2nd Convolution Block\n",
    "    model.add(Conv2D(128, (5, 5), activation='relu', padding='same'))\n",
    "    model.add(BatchNormalization())\n",
    "    model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "    model.add(Dropout(0.25))\n",
    "\n",
    "    # 3rd Convolution Block\n",
    "    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))\n",
    "    model.add(BatchNormalization())\n",
    "    model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "    model.add(Dropout(0.25))\n",
    "\n",
    "    # 4th Convolution Block\n",
    "    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))\n",
    "    model.add(BatchNormalization())\n",
    "    model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "    model.add(Dropout(0.25))\n",
    "\n",
    "    # Flatten and Dense\n",
    "    model.add(Flatten())\n",
    "    \n",
    "    model.add(Dense(256, activation='relu'))\n",
    "    model.add(BatchNormalization())\n",
    "    model.add(Dropout(0.5))\n",
    "    \n",
    "    model.add(Dense(512, activation='relu'))\n",
    "    model.add(BatchNormalization())\n",
    "    model.add(Dropout(0.5))\n",
    "\n",
    "    # Output\n",
    "    model.add(Dense(num_classes, activation='softmax'))\n",
    "\n",
    "    model.compile(optimizer=Adam(learning_rate=0.0001), \n",
    "                  loss='categorical_crossentropy', \n",
    "                  metrics=['accuracy'])\n",
    "    \n",
    "    return model\n",
    "\n",
    "model = build_model()\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Model Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 4. Model Training with Augmentation and Class Weights\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau, EarlyStopping\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "from sklearn.utils.class_weight import compute_class_weight\n",
    "import numpy as np\n",
    "\n",
    "BATCH_SIZE = 64\n",
    "EPOCHS = 100\n",
    "\n",
    "# Compute Class Weights\n",
    "y_train_ints = np.argmax(y_train_onehot, axis=1)\n",
    "class_weights = compute_class_weight(\n",
    "    class_weight='balanced',\n",
    "    classes=np.unique(y_train_ints),\n",
    "    y=y_train_ints\n",
    ")\n",
    "class_weight_dict = dict(enumerate(class_weights))\n",
    "print(f'Computed Class Weights: {class_weight_dict}')\n",
    "\n",
    "# Define Callbacks\n",
    "checkpoint = ModelCheckpoint('Models/emotion_model_nb.keras', monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')\n",
    "reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=0.00001, mode='min')\n",
    "early_stop = EarlyStopping(monitor='val_loss', patience=15, mode='min', restore_best_weights=True)\n",
    "callbacks_list = [checkpoint, reduce_lr, early_stop]\n",
    "\n",
    "# Setup Data Augmentation\n",
    "print('\\nSetting up ImageDataGenerator...')\n",
    "datagen = ImageDataGenerator(\n",
    "    rotation_range=10,\n",
    "    width_shift_range=0.1,\n",
    "    height_shift_range=0.1,\n",
    "    zoom_range=0.1,\n",
    "    horizontal_flip=True,\n",
    "    fill_mode='nearest'\n",
    ")\n",
    "\n",
    "# Train the model\n",
    "print('\\nStarting Model Training with Augmentation...')\n",
    "history = model.fit(\n",
    "    datagen.flow(X_train, y_train_onehot, batch_size=BATCH_SIZE),\n",
    "    validation_data=(X_test, y_test_onehot),\n",
    "    epochs=EPOCHS,\n",
    "    callbacks=callbacks_list,\n",
    "    class_weight=class_weight_dict\n",
    ")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 5. Evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_history(history):\n",
    "    acc = history.history['accuracy']\n",
    "    val_acc = history.history['val_accuracy']\n",
    "    loss = history.history['loss']\n",
    "    val_loss = history.history['val_loss']\n",
    "    epochs = range(len(acc))\n",
    "\n",
    "    plt.figure(figsize=(12, 5))\n",
    "    plt.subplot(1, 2, 1)\n",
    "    plt.plot(epochs, acc, label='Training Accuracy')\n",
    "    plt.plot(epochs, val_acc, label='Validation Accuracy')\n",
    "    plt.title('Accuracy')\n",
    "    plt.legend()\n",
    "\n",
    "    plt.subplot(1, 2, 2)\n",
    "    plt.plot(epochs, loss, label='Training Loss')\n",
    "    plt.plot(epochs, val_loss, label='Validation Loss')\n",
    "    plt.title('Loss')\n",
    "    plt.legend()\n",
    "    plt.show()\n",
    "\n",
    "plot_history(history)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 6. Real-Time Detection (Webcam)\n",
    "Run the following cell to start the webcam. Press **'q'** to quit the window."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Webcam started. Press 'q' to quit.\n"
     ]
    }
   ],
   "source": [
    "import cv2\n",
    "import numpy as np\n",
    "from tensorflow.keras.models import load_model\n",
    "\n",
    "# Load trained model (ensure this path matches where you saved it)\n",
    "model = load_model('Models/emotion_model_final_v1.keras')\n",
    "\n",
    "# Emotion Labels\n",
    "EMOTION_LABELS = {0: 'Anger', 1: 'Fear', 2: 'Happy', 3: 'Sad', 4: 'Surprise', 5: 'Neutral'}\n",
    "\n",
    "# Load Face Cascade\n",
    "face_cascade_path = cv2.data.haarcascades + 'haarcascade_frontalface_default.xml'\n",
    "face_cascade = cv2.CascadeClassifier(face_cascade_path)\n",
    "\n",
    "# Start Webcam\n",
    "cap = cv2.VideoCapture(0)\n",
    "\n",
    "if not cap.isOpened():\n",
    "    print(\"Could not open webcam\")\n",
    "else:\n",
    "    print(\"Webcam started. Press 'q' to quit.\")\n",
    "    while True:\n",
    "        ret, frame = cap.read()\n",
    "        if not ret:\n",
    "            break\n",
    "        \n",
    "        # Mirror image\n",
    "        frame = cv2.flip(frame, 1)\n",
    "        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)\n",
    "        \n",
    "        faces = face_cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=5)\n",
    "        \n",
    "        for (x, y, w, h) in faces:\n",
    "            # Preprocess face\n",
    "            roi_gray = gray[y:y+h, x:x+w]\n",
    "            roi_gray = cv2.resize(roi_gray, (48, 48))\n",
    "            roi_gray = roi_gray.astype('float32') / 255.0\n",
    "            roi_gray = np.expand_dims(roi_gray, axis=0)\n",
    "            roi_gray = np.expand_dims(roi_gray, axis=-1)\n",
    "            \n",
    "            # Predict\n",
    "            prediction = model.predict(roi_gray, verbose=0)\n",
    "            max_index = int(np.argmax(prediction))\n",
    "            label = EMOTION_LABELS[max_index]\n",
    "            confidence = prediction[0][max_index]\n",
    "            \n",
    "            # Draw\n",
    "            cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)\n",
    "            cv2.putText(frame, f\"{label} ({confidence:.2f})\", (x, y-10), \n",
    "                        cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)\n",
    "        \n",
    "        cv2.imshow('Facial Emotion Detection', frame)\n",
    "        \n",
    "        if cv2.waitKey(1) & 0xFF == ord('q'):\n",
    "            break\n",
    "            \n",
    "    cap.release()\n",
    "    cv2.destroyAllWindows()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}