import os
import time

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, models, transforms

# Configuration and Paths
DATA_DIR = 'dataset'
NUM_CLASSES = 10
BATCH_SIZE = 32
NUM_EPOCHS = 10
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

print(f"Running on device: {DEVICE}")

# Data Pipeline and Preprocessing
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

image_datasets = {
    x: datasets.ImageFolder(os.path.join(DATA_DIR, x), data_transforms[x]) 
    for x in ['train', 'val']
}

dataloaders = {
    x: torch.utils.data.DataLoader(image_datasets[x], batch_size=BATCH_SIZE, shuffle=True) 
    for x in ['train', 'val']
}

class_names = image_datasets['train'].classes
print(f"Found {len(class_names)} classes: {class_names}")

# Load Pretrained EfficientNet-B0 and Modify Classifier
try:
    weights = models.EfficientNet_B0_Weights.DEFAULT
    model = models.efficientnet_b0(weights=weights)
except AttributeError:
    model = models.efficientnet_b0(pretrained=True)

num_ftrs = model.classifier[1].in_features
model.classifier[1] = nn.Linear(num_ftrs, NUM_CLASSES)
model = model.to(DEVICE)

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Training Loop
best_acc = 0.0
start_time = time.time()

for epoch in range(NUM_EPOCHS):
    print(f'\nEpoch {epoch+1}/{NUM_EPOCHS}')
    print('-' * 15)

    for phase in ['train', 'val']:
        if phase == 'train':
            model.train()
        else:
            model.eval()

        running_loss = 0.0
        running_corrects = 0

        for inputs, labels in dataloaders[phase]:
            inputs, labels = inputs.to(DEVICE), labels.to(DEVICE)
            optimizer.zero_grad()

            with torch.set_grad_enabled(phase == 'train'):
                outputs = model(inputs)
                _, preds = torch.max(outputs, 1)
                loss = criterion(outputs, labels)

                if phase == 'train':
                    loss.backward()
                    optimizer.step()

            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)

        epoch_loss = running_loss / len(image_datasets[phase])
        epoch_acc = running_corrects.double() / len(image_datasets[phase])
        print(f'[{phase.upper()}] Loss: {epoch_loss:.4f} | Accuracy: {epoch_acc:.4f}')

        # Save the best model
        if phase == 'val' and epoch_acc > best_acc:
            best_acc = epoch_acc
            torch.save(model.state_dict(), 'best_thai_food_model.pth')
            print("Best model updated and saved.")

time_elapsed = time.time() - start_time
print(f'\nTraining complete in {time_elapsed // 60:.0f}m {time_elapsed % 60:.0f}s')
print(f'Highest Validation Accuracy: {best_acc:.4f}')