Terrain_V6 Optimizer RMSpop.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Importing necessary Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Install necessary packages and import libraries\n",
    "# The first few lines ensure that TensorFlow, Scipy, and Matplotlib are installed.\n",
    "# pip install tensorflow\n",
    "# pip install scipy\n",
    "# pip install matplotlib\n",
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Inline plotting with Matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# %matplotlib inline\n",
    "# this  command ensures that plots are displayed directly in the notebook after being generated."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Building a Convolutional Neural Network (CNN) model for terrain classification\n",
    "# Importing layers from Keras for building the model architecture\n",
    "from keras.preprocessing import image\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Conv2D\n",
    "from keras.layers import MaxPooling2D\n",
    "from keras.layers import Flatten\n",
    "from keras.layers import Dense\n",
    "from keras.layers import Dropout\n",
    "from keras.layers import BatchNormalization\n",
    "from keras.models import load_model\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "from tensorflow.keras.callbacks import LearningRateScheduler, ReduceLROnPlateau\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Defining the CNN model\n",
    "The following code defines a CNN model using TensorFlow's Keras API. The model is designed for terrain classification with a series of convolutional layers, pooling layers, and fully connected layers.\n",
    "\n",
    "* **Convolutional Layers:** These layers apply filters to the input image, helping to detect various features (like edges, textures, etc.).\n",
    "* **Max Pooling:** This operation reduces the spatial dimensions (width and height) of the output from the convolutional layers, which helps in reducing computational complexity and controlling overfitting.\n",
    "* **Batch Normalization:** This technique normalizes the outputs of a previous activation layer, which helps stabilize learning and can accelerate training.\n",
    "* **Dropout Layers:** These layers randomly set a fraction of the input units to zero during training to help prevent overfitting.\n",
    "* **Softmax Layer:** This is used in the output layer for multi-class classification problems, providing probabilities for each class.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the CNN model architecture with residual connections\n",
    "def create_model():\n",
    "    model = tf.keras.Sequential([\n",
    "        tf.keras.layers.Input(shape=(64, 64, 3)),\n",
    "        tf.keras.layers.Conv2D(32, kernel_size=3, activation='relu'),\n",
    "        tf.keras.layers.MaxPooling2D(pool_size=2, strides=2),\n",
    "        tf.keras.layers.BatchNormalization(),\n",
    "\n",
    "        tf.keras.layers.Conv2D(64, kernel_size=3, activation='relu'),\n",
    "        tf.keras.layers.MaxPooling2D(pool_size=2, strides=2),\n",
    "        tf.keras.layers.BatchNormalization(),\n",
    "\n",
    "        tf.keras.layers.Conv2D(128, kernel_size=3, activation='relu'),\n",
    "        tf.keras.layers.MaxPooling2D(pool_size=2, strides=2),\n",
    "        tf.keras.layers.BatchNormalization(),\n",
    "\n",
    "        tf.keras.layers.Flatten(),\n",
    "\n",
    "        tf.keras.layers.Dense(1024, activation='relu'),\n",
    "        tf.keras.layers.Dropout(0.2),\n",
    "        tf.keras.layers.BatchNormalization(),\n",
    "\n",
    "        tf.keras.layers.Dense(1024, activation='relu'),\n",
    "        tf.keras.layers.Dropout(0.2),\n",
    "        tf.keras.layers.BatchNormalization(),\n",
    "\n",
    "        tf.keras.layers.Dense(256, activation='relu'),\n",
    "        tf.keras.layers.Dropout(0.2),\n",
    "        tf.keras.layers.BatchNormalization(),\n",
    "\n",
    "        tf.keras.layers.Dense(5, activation='softmax')\n",
    "    ])\n",
    "    return model\n",
    "\n",
    "model = create_model()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Compiling the CNN model\n",
    "The model is compiled using the Adam optimizer, with categorical crossentropy as the loss function, and accuracy as the evaluation metric."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Compile the model\n",
    "# Categorical crossentropy is used since the labels are one-hot encoded.\n",
    "# Adam optimizer is used for its adaptive learning rate.\n",
    "\n",
    "model.compile(optimizer=tf.keras.optimizers.RMSprop(learning_rate=0.001), loss='categorical_crossentropy', metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data Augmentation and Preprocessing\n",
    "This section applies data augmentation techniques using the `ImageDataGenerator` from Keras to generate more training samples and preprocess the images. These operations include rescaling, rotating, shifting, and flipping.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data augmentation and preprocessing for training and validation datasets\n",
    "# The ImageDataGenerator applies various transformations to augment the training data\n",
    "# Data augmentation for training dataset\n",
    "train_datagen = ImageDataGenerator(\n",
    "    rescale=1./255,\n",
    "    shear_range=0.2,\n",
    "    zoom_range=0.2,\n",
    "    horizontal_flip=True,\n",
    "    rotation_range=30,\n",
    "    brightness_range=[0.8, 1.2],\n",
    "    width_shift_range=0.2,\n",
    "    height_shift_range=0.2\n",
    ")\n",
    "\n",
    "# Validation dataset (only rescaling)\n",
    "test_datagen = ImageDataGenerator(rescale=1./255)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Loading and Preparing the Data\n",
    "In this section, the training and validation data are loaded from the respective directories, and the images are prepared for the model using the augmentation techniques defined earlier.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 10000 images belonging to 5 classes.\n",
      "Found 500 images belonging to 5 classes.\n"
     ]
    }
   ],
   "source": [
    "# Assuming you've created 'train_subset' and 'test_subset' directories\n",
    "training_set = train_datagen.flow_from_directory(\n",
    "    r\"D:\\Jupyter Notebook\\Contribution\\Terrain-Recognition\\Data Main\\Training Data\",\n",
    "    target_size=(64, 64),\n",
    "    batch_size=64,\n",
    "    class_mode='categorical'\n",
    ")\n",
    "\n",
    "test_set = test_datagen.flow_from_directory(\n",
    "    r\"D:\\Jupyter Notebook\\Contribution\\Terrain-Recognition\\Data Main\\Testing Data\",\n",
    "    target_size=(64, 64),\n",
    "    batch_size=64,\n",
    "    class_mode='categorical'\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define learning rate scheduler\n",
    "def scheduler(epoch, lr):\n",
    "    if epoch < 10:\n",
    "        return 1e-2\n",
    "    else:\n",
    "        return 1e-3\n",
    "\n",
    "lr_schedule = LearningRateScheduler(scheduler)\n",
    "lr_reduction = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3, min_lr=1e-6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "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\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential\"\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\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                         </span>┃<span style=\"font-weight: bold\"> Output Shape                </span>┃<span style=\"font-weight: bold\">         Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
       "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">62</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">62</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)         │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">31</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">31</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)          │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization                  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">31</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">31</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">29</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">29</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)          │          <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)          │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_1                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)         │          <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)           │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_2                │ (<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\">128</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</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\">4608</span>)                │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)                │       <span style=\"color: #00af00; text-decoration-color: #00af00\">4,719,616</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)                │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_3                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)                │           <span style=\"color: #00af00; text-decoration-color: #00af00\">4,096</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)                │       <span style=\"color: #00af00; text-decoration-color: #00af00\">1,049,600</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\">1024</span>)                │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_4                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)                │           <span style=\"color: #00af00; text-decoration-color: #00af00\">4,096</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</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\">256</span>)                 │         <span style=\"color: #00af00; text-decoration-color: #00af00\">262,400</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dropout_2 (<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\">256</span>)                 │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_5                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)                 │           <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</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\">1,285</span> │\n",
       "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                        \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape               \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m        Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
       "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m32\u001b[0m)          │             \u001b[38;5;34m896\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)         │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m31\u001b[0m, \u001b[38;5;34m31\u001b[0m, \u001b[38;5;34m32\u001b[0m)          │               \u001b[38;5;34m0\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization                  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m31\u001b[0m, \u001b[38;5;34m31\u001b[0m, \u001b[38;5;34m32\u001b[0m)          │             \u001b[38;5;34m128\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m64\u001b[0m)          │          \u001b[38;5;34m18,496\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m64\u001b[0m)          │               \u001b[38;5;34m0\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_1                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m64\u001b[0m)          │             \u001b[38;5;34m256\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m128\u001b[0m)         │          \u001b[38;5;34m73,856\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m128\u001b[0m)           │               \u001b[38;5;34m0\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_2                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m128\u001b[0m)           │             \u001b[38;5;34m512\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4608\u001b[0m)                │               \u001b[38;5;34m0\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dense (\u001b[38;5;33mDense\u001b[0m)                        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)                │       \u001b[38;5;34m4,719,616\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dropout (\u001b[38;5;33mDropout\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)                │               \u001b[38;5;34m0\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_3                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)                │           \u001b[38;5;34m4,096\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)                │       \u001b[38;5;34m1,049,600\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)                  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)                │               \u001b[38;5;34m0\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_4                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)                │           \u001b[38;5;34m4,096\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)                 │                             │                 │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)                 │         \u001b[38;5;34m262,400\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m)                  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)                 │               \u001b[38;5;34m0\u001b[0m │\n",
       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
       "│ batch_normalization_5                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)                 │           \u001b[38;5;34m1,024\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\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;34m1,285\u001b[0m │\n",
       "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\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\">6,136,261</span> (23.41 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m6,136,261\u001b[0m (23.41 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\">6,131,205</span> (23.39 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m6,131,205\u001b[0m (23.39 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\">5,056</span> (19.75 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m5,056\u001b[0m (19.75 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Training the CNN Model\n",
    "The model is trained using the training and validation data. The training process is monitored, and a learning rate scheduler is used to adjust the learning rate dynamically during training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/20\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\DEEPANSHU\\anaconda3\\Lib\\site-packages\\keras\\src\\trainers\\data_adapters\\py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
      "  self._warn_if_super_not_called()\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m157/256\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m59s\u001b[0m 598ms/step - accuracy: 0.4809 - loss: 1.6547 "
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\DEEPANSHU\\anaconda3\\Lib\\contextlib.py:155: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n",
      "  self.gen.throw(typ, value, traceback)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m112s\u001b[0m 383ms/step - accuracy: 0.5007 - loss: 1.5152 - val_accuracy: 0.4576 - val_loss: 3.1644 - learning_rate: 0.0100\n",
      "Epoch 2/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 394ms/step - accuracy: 0.6165 - loss: 1.0032 - val_accuracy: 0.5385 - val_loss: 1.2318 - learning_rate: 0.0100\n",
      "Epoch 3/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m104s\u001b[0m 392ms/step - accuracy: 0.6501 - loss: 0.9081 - val_accuracy: 0.5045 - val_loss: 1.5537 - learning_rate: 0.0100\n",
      "Epoch 4/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m104s\u001b[0m 390ms/step - accuracy: 0.6743 - loss: 0.8713 - val_accuracy: 0.6346 - val_loss: 0.8987 - learning_rate: 0.0100\n",
      "Epoch 5/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 401ms/step - accuracy: 0.6839 - loss: 0.8343 - val_accuracy: 0.7165 - val_loss: 0.7236 - learning_rate: 0.0100\n",
      "Epoch 6/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m105s\u001b[0m 392ms/step - accuracy: 0.6954 - loss: 0.8058 - val_accuracy: 0.6346 - val_loss: 0.9649 - learning_rate: 0.0100\n",
      "Epoch 7/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m105s\u001b[0m 393ms/step - accuracy: 0.7064 - loss: 0.7798 - val_accuracy: 0.6562 - val_loss: 1.0304 - learning_rate: 0.0100\n",
      "Epoch 8/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m104s\u001b[0m 389ms/step - accuracy: 0.7156 - loss: 0.7612 - val_accuracy: 0.7308 - val_loss: 0.7392 - learning_rate: 0.0100\n",
      "Epoch 9/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m107s\u001b[0m 401ms/step - accuracy: 0.7262 - loss: 0.7382 - val_accuracy: 0.6964 - val_loss: 0.8319 - learning_rate: 0.0100\n",
      "Epoch 10/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m104s\u001b[0m 389ms/step - accuracy: 0.7194 - loss: 0.7499 - val_accuracy: 0.7115 - val_loss: 0.7380 - learning_rate: 0.0100\n",
      "Epoch 11/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 397ms/step - accuracy: 0.7384 - loss: 0.6969 - val_accuracy: 0.7969 - val_loss: 0.5023 - learning_rate: 0.0010\n",
      "Epoch 12/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m105s\u001b[0m 395ms/step - accuracy: 0.7638 - loss: 0.6394 - val_accuracy: 0.7885 - val_loss: 0.5396 - learning_rate: 0.0010\n",
      "Epoch 13/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 400ms/step - accuracy: 0.7623 - loss: 0.6412 - val_accuracy: 0.7879 - val_loss: 0.5226 - learning_rate: 0.0010\n",
      "Epoch 14/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m104s\u001b[0m 390ms/step - accuracy: 0.7662 - loss: 0.6334 - val_accuracy: 0.8462 - val_loss: 0.4046 - learning_rate: 0.0010\n",
      "Epoch 15/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m105s\u001b[0m 394ms/step - accuracy: 0.7693 - loss: 0.6308 - val_accuracy: 0.8348 - val_loss: 0.4446 - learning_rate: 0.0010\n",
      "Epoch 16/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m103s\u001b[0m 387ms/step - accuracy: 0.7666 - loss: 0.6179 - val_accuracy: 0.7308 - val_loss: 0.7355 - learning_rate: 0.0010\n",
      "Epoch 17/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m106s\u001b[0m 396ms/step - accuracy: 0.7636 - loss: 0.6286 - val_accuracy: 0.8371 - val_loss: 0.4924 - learning_rate: 0.0010\n",
      "Epoch 18/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m86s\u001b[0m 320ms/step - accuracy: 0.7753 - loss: 0.6065 - val_accuracy: 0.8846 - val_loss: 0.3848 - learning_rate: 0.0010\n",
      "Epoch 19/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m78s\u001b[0m 293ms/step - accuracy: 0.7759 - loss: 0.6039 - val_accuracy: 0.8192 - val_loss: 0.5040 - learning_rate: 0.0010\n",
      "Epoch 20/20\n",
      "\u001b[1m256/256\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 258ms/step - accuracy: 0.7771 - loss: 0.6035 - val_accuracy: 0.8846 - val_loss: 0.3493 - learning_rate: 0.0010\n"
     ]
    }
   ],
   "source": [
    "# Train the model\n",
    "modelZ = model.fit(\n",
    "    training_set,\n",
    "    steps_per_epoch=256,\n",
    "    epochs=20,\n",
    "    validation_data=test_set,\n",
    "    validation_steps=7,\n",
    "    callbacks=[lr_schedule, lr_reduction]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting Training and Validation Accuracy\n",
    "This section plots the training and validation accuracy and loss over time to visualize how the model performs during training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Final Training Accuracy: 0.7767\n",
      "Final Validation Accuracy: 0.8846\n"
     ]
    }
   ],
   "source": [
    "# Print the final training and validation accuracy\n",
    "train_accuracy = modelZ.history['accuracy'][-1]\n",
    "val_accuracy = modelZ.history['val_accuracy'][-1]\n",
    "\n",
    "print(f\"Final Training Accuracy: {train_accuracy:.4f}\")\n",
    "print(f\"Final Validation Accuracy: {val_accuracy:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x1600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot training and validation accuracy over epochs\n",
    "plt.figure(figsize=(12, 16))\n",
    "\n",
    "plt.subplot(4, 2, 1)\n",
    "plt.plot(modelZ.history['loss'], label='Loss')\n",
    "plt.plot(modelZ.history['val_loss'], label='val_Loss')\n",
    "plt.title('Loss Function Evolution')\n",
    "plt.legend()\n",
    "\n",
    "plt.subplot(4, 2, 2)\n",
    "plt.plot(modelZ.history['accuracy'], label='Accuracy')\n",
    "plt.plot(modelZ.history['val_accuracy'], label='val_accuracy')\n",
    "plt.title('Accuracy Function Evolution')\n",
    "plt.legend()\n",
    "\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Saving the Trained Model\n",
    "After training, the model is saved to a file for future use.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# model.save('modelZ.h5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from tensorflow.keras.models import load_model\n",
    "\n",
    "# # Load the model\n",
    "# model = load_model('saved_model/my_model')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# print(\"Num GPUs Available: \", len(tf.config.list_physical_devices('GPU')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}