{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Convolutional Neural Network (CNN) Example\n",
        "\n",
        "<!--\n",
        "Project: PyTorch Neural Networks\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 building and training a Convolutional Neural Network for image classification.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# CNN Example\n",
        "# Project: PyTorch Neural Networks\n",
        "# Author: RSK World\n",
        "# Website: https://rskworld.in\n",
        "# Email: help@rskworld.in\n",
        "# Phone: +91 93305 39277\n",
        "\n",
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.utils.data import DataLoader, TensorDataset\n",
        "import matplotlib.pyplot as plt\n",
        "import sys\n",
        "\n",
        "sys.path.append('..')\n",
        "from models.cnn import SimpleCNN\n",
        "from training.trainer import Trainer\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Prepare Image Data\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Generate synthetic image data (28x28 grayscale images)\n",
        "# In practice, you would load real image datasets like MNIST, CIFAR-10, etc.\n",
        "\n",
        "X_train = torch.randn(200, 1, 28, 28)  # (batch, channels, height, width)\n",
        "y_train = torch.randint(0, 10, (200,))\n",
        "X_test = torch.randn(50, 1, 28, 28)\n",
        "y_test = torch.randint(0, 10, (50,))\n",
        "\n",
        "print(f\"Training set: {X_train.shape}, Labels: {y_train.shape}\")\n",
        "print(f\"Test set: {X_test.shape}, Labels: {y_test.shape}\")\n",
        "\n",
        "# Create data loaders\n",
        "train_dataset = TensorDataset(X_train, y_train)\n",
        "test_dataset = TensorDataset(X_test, y_test)\n",
        "train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\n",
        "test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Create and Train CNN\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Create CNN model\n",
        "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
        "model = SimpleCNN(num_classes=10).to(device)\n",
        "\n",
        "# Define loss and optimizer\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
        "\n",
        "# Train model\n",
        "trainer = Trainer(model, criterion, optimizer, device)\n",
        "history = trainer.train(train_loader, test_loader, epochs=15)\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Visualize Results\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from training.utils import plot_training_history\n",
        "\n",
        "plot_training_history(history)\n",
        "\n"
      ]
    }
  ],
  "metadata": {
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}