"""
Convolutional Neural Network Model
Project: PyTorch Neural Networks
Author: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277
Description: CNN implementation for image classification
"""

import torch
import torch.nn as nn
import torch.nn.functional as F


class SimpleCNN(nn.Module):
    """
    Simple Convolutional Neural Network
    
    A CNN architecture suitable for image classification tasks.
    Demonstrates PyTorch's Conv2d, MaxPool2d, and other CNN layers.
    """
    
    def __init__(self, num_classes=10, dropout=0.5):
        """
        Initialize the CNN
        
        Args:
            num_classes: Number of output classes
            dropout: Dropout probability
        """
        super(SimpleCNN, self).__init__()
        
        # Convolutional layers
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, padding=1)
        self.conv3 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, padding=1)
        
        # Pooling layer
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
        
        # Batch normalization
        self.bn1 = nn.BatchNorm2d(32)
        self.bn2 = nn.BatchNorm2d(64)
        self.bn3 = nn.BatchNorm2d(128)
        
        # Fully connected layers
        # After 3 pooling operations: 28 -> 14 -> 7 -> 3 (with padding)
        # So 128 * 3 * 3 = 1152
        self.fc1 = nn.Linear(128 * 3 * 3, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, num_classes)
        
        self.dropout = nn.Dropout(dropout)
    
    def forward(self, x):
        """
        Forward pass through the CNN
        
        Args:
            x: Input tensor of shape (batch_size, channels, height, width)
            
        Returns:
            Output tensor of shape (batch_size, num_classes)
        """
        # First conv block
        x = self.conv1(x)
        x = self.bn1(x)
        x = F.relu(x)
        x = self.pool(x)
        
        # Second conv block
        x = self.conv2(x)
        x = self.bn2(x)
        x = F.relu(x)
        x = self.pool(x)
        
        # Third conv block
        x = self.conv3(x)
        x = self.bn3(x)
        x = F.relu(x)
        x = self.pool(x)
        
        # Flatten
        x = x.view(x.size(0), -1)
        
        # Fully connected layers
        x = F.relu(self.fc1(x))
        x = self.dropout(x)
        x = F.relu(self.fc2(x))
        x = self.dropout(x)
        x = self.fc3(x)
        
        return x
    
    def predict(self, x):
        """
        Make predictions on input data
        
        Args:
            x: Input tensor
            
        Returns:
            Predicted class indices
        """
        self.eval()
        with torch.no_grad():
            outputs = self.forward(x)
            _, predicted = torch.max(outputs.data, 1)
        return predicted