{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Convolutional Neural Networks (CNNs) with TensorFlow\n",
    "\n",
    "<!--\n",
    "Project: TensorFlow Deep Learning\n",
    "Author: RSK World\n",
    "Website: https://rskworld.in\n",
    "Email: help@rskworld.in\n",
    "Phone: +91 93305 39277\n",
    "-->\n",
    "\n",
    "This notebook demonstrates CNN construction for image classification."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "import os\n",
    "sys.path.append(os.path.join(os.path.dirname(os.getcwd()), 'src'))\n",
    "\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from cnns import (\n",
    "    create_simple_cnn,\n",
    "    create_deep_cnn,\n",
    "    create_resnet_cnn,\n",
    "    visualize_cnn_layers\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load CIFAR-10 Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load CIFAR-10 dataset\n",
    "(X_train, y_train), (X_test, y_test) = keras.datasets.cifar10.load_data()\n",
    "\n",
    "# Preprocess data\n",
    "X_train = X_train.astype('float32') / 255.0\n",
    "X_test = X_test.astype('float32') / 255.0\n",
    "\n",
    "print(f\"Training samples: {X_train.shape[0]}\")\n",
    "print(f\"Test samples: {X_test.shape[0]}\")\n",
    "print(f\"Image shape: {X_train.shape[1:]}\")\n",
    "print(f\"Number of classes: {len(np.unique(y_train))}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create Simple CNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create simple CNN\n",
    "model = create_simple_cnn(input_shape=(32, 32, 3), num_classes=10)\n",
    "\n",
    "# Display model architecture\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train model\n",
    "history = model.fit(\n",
    "    X_train, y_train,\n",
    "    batch_size=128,\n",
    "    epochs=10,\n",
    "    validation_data=(X_test, y_test),\n",
    "    verbose=1\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluate Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Evaluate model\n",
    "test_loss, test_accuracy = model.evaluate(X_test, y_test, verbose=0)\n",
    "print(f\"Test Accuracy: {test_accuracy:.4f}\")\n",
    "print(f\"Test Loss: {test_loss:.4f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create Deep CNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create deep CNN with batch normalization\n",
    "deep_model = create_deep_cnn(input_shape=(32, 32, 3), num_classes=10)\n",
    "deep_model.summary()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}