import torch
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

# Define transformations
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))  # Normalize to [-1, 1]
])

# Load CIFAR-10 dataset
train_dataset = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)

# Create data loaders
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

print(f"Training Data Size: {len(train_dataset)}")
print(f"Test Data Size: {len(test_dataset)}")

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

# Define the CNN model
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        # self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)
        # self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
        # self.pool = nn.MaxPool2d(2, 2)
        # self.fc1 = nn.Linear(64 * 8 * 8, 512)
        # self.fc2 = nn.Linear(512, 10)
        # self.dropout = nn.Dropout(0.5)
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # x = F.relu(self.conv1(x))
        # x = self.pool(F.relu(self.conv2(x)))
        # x = x.view(-1, 64 * 8 * 8)  # Flatten the tensor
        # x = F.relu(self.fc1(x))
        # x = self.dropout(x)
        # x = self.fc2(x)
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

model = CNN()
print(model)

import torch.optim as optim

# Define loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Training loop
def train_model(model, train_loader, criterion, optimizer, epochs=1):
    model.train()
    for epoch in range(epochs):
        running_loss = 0.0
        for images, labels in train_loader:
            # Zero gradients
            optimizer.zero_grad()

            # Forward pass
            outputs = model(images)
            loss = criterion(outputs, labels)

            # Backward pass and optimize
            loss.backward()
            optimizer.step()

            running_loss += loss.item()
        print(f"Epoch {epoch+1}, Loss: {running_loss/len(train_loader):.4f}")

train_model(model, train_loader, criterion, optimizer)

# Evaluation loop
def evaluate_model(model, test_loader):
    model.eval()
    correct = 0
    total = 0
    with torch.no_grad():
        for images, labels in test_loader:
            outputs = model(images)
            _, predicted = torch.max(outputs, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print(f"Test Accuracy: {100 * correct / total:.2f}%")

evaluate_model(model, test_loader)