import torch
import torch.nn as nn
import torch.nn.functional as F  # Add this line
import torchvision
import torchvision.transforms as transforms


# Device configuration
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Hyper-parameters
num_epochs = 5
batch_size = 4
learning_rate = 0.001

# Dataset has PILImage images of range [0, 1].
# We transform them to Tensors of normalized range [-1, 1]
transform = transforms.Compose([transforms.ToTensor()])

# CIFAR10: 60000 32x32 color images in 10 classes, with 6000 images per class
# train_dataset = torchvision.datasets.CIFAR10(root="./data", train=True, download=True, transform=transform)
train_dataset = torchvision.datasets.MNIST(root="./data", train=True, download=True, transform=transform)


# test_dataset = torchvision.datasets.CIFAR10(root="./data", train=False, download=True, transform=transform)
test_dataset = torchvision.datasets.MNIST(root="./data", train=False, download=True, transform=transform)

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)

test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)


class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 3, 1, 1)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 10)
        # self.fc2 = nn.Linear(120, 84)
        # self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        # x = F.relu(self.fc1(x))
        # x = F.relu(self.fc2(x))
        # x = self.fc3(x)

        x = self.fc1(x)
        return x


model = ConvNet().to(device)

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)


# Train the model
n_total_steps = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

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

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

        if (i + 1) % 2000 == 0:
            print(f"Epoch [{epoch+1}/{num_epochs}], Step [{i+1}/{n_total_steps}], Loss: {loss.item():.4f}")

print("Finished Training")

# Test the model
with torch.no_grad():
    n_correct = 0
    n_samples = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)

        # max returns (value ,index)
        _, predicted = torch.max(outputs.data, 1)
        n_samples += labels.size(0)
        n_correct += (predicted == labels).sum().item()

    acc = 100.0 * n_correct / n_samples
    print(f"Accuracy of the network on the 10000 test images: {acc} %")