import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
import torchvision
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
import os

# Set device (GPU if available, otherwise CPU)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Define data transforms
data_transforms = transforms.Compose([
    transforms.Resize(32),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])

# Load dataset
dataset = ImageFolder(root="./synthetic_dataset", transform=data_transforms)

# Create data loader
batch_size = 32
data_loader = DataLoader(dataset, batch_size=batch_size, shuffle=True)

# Define CNN model
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(6 * 14 * 14, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 3)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = x.view(-1, 6 * 14 * 14)
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

model = CNN().to(device)

# Define loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3)

# Train model
for epoch in range(5):
    running_loss = 0.0
    for i, data in enumerate(data_loader):
        inputs, labels = data
        inputs, labels = inputs.to(device), labels.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    avg_loss = running_loss / (i + 1)
    print(f"Epoch {epoch+1}/5 — Loss: {avg_loss:.4f}")

# Save model weights
torch.save(model.state_dict(), "best_model.pt")
print("Training complete. Model saved to best_model.pt")