import torch
import torchvision
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader, random_split
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

# epochs
num_epochs = 20

# Dataset path
dataset_path = "./dataset"

# Transforms
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

# Load dataset
dataset = ImageFolder(root=dataset_path, transform=transform)

# Split dataset
train_size = int(0.9 * len(dataset))
test_size = len(dataset) - train_size
train_dataset, test_dataset = random_split(dataset, [train_size, test_size])

# Data loaders
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)

class CustomCNN(nn.Module):
    def __init__(self):
        super(CustomCNN, self).__init__()
        self.dropout = nn.Dropout(0.2)  # Dropout layer with 20% probability
        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1)
        self.conv4 = nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=0)
        self.fc1 = nn.Linear(256 * 14 * 14, 1024)  # Adjusted for 224x224 input size
        self.fc2 = nn.Linear(1024, 512)
        self.fc3 = nn.Linear(512, len(dataset.classes))

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.pool(F.relu(self.conv3(x)))
        x = self.pool(F.relu(self.conv4(x)))
        x = x.view(-1, 256 * 14 * 14)
        x = self.dropout(F.relu(self.fc1(x)))
        x = self.dropout(F.relu(self.fc2(x)))
        x = self.fc3(x)
        return x

model = CustomCNN()

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.1)  # Reduces LR every 5 epochs

def calculate_accuracy(loader, model):
    correct = 0
    total = 0
    with torch.no_grad():
        for data in loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    return 100 * correct / total

for epoch in range(num_epochs):
    model.train()  # Set the model to training mode
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()

    # Update the learning rate
    scheduler.step()

    # Calculate training and test accuracy
    model.eval()  # Set the model to evaluation mode
    train_accuracy = calculate_accuracy(train_loader, model)
    test_accuracy = calculate_accuracy(test_loader, model)

    print(f"Epoch {epoch + 1}, Loss: {running_loss / len(train_loader)}, Train Accuracy: {train_accuracy}%, Test Accuracy: {test_accuracy}%")

# save the final model after all epochs
torch.save(model.state_dict(), 'final_model.pth')