import os
import time
import copy

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

# Training parameters
num_epochs = 25
batch_size = 32
learning_rate = 0.001
data_dir = '/kaggle/input/centraasia'  # Root folder with subdirectories train, val, and test

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

# Loading datasets using ImageFolder
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val', 'test']}

dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x],
                                              batch_size=batch_size,
                                              shuffle=True,
                                              num_workers=4)
               for x in ['train', 'val', 'test']}

dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val', 'test']}
class_names = image_datasets['train'].classes

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

# Initializing the ResNet50 model
model_ft = models.resnet50(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, len(class_names))

model_ft = model_ft.to(device)

# If multiple GPUs are available, wrap the model in DataParallel
if torch.cuda.device_count() > 1:
    model_ft = nn.DataParallel(model_ft)

# Loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer_ft = optim.SGD(model_ft.parameters(), lr=learning_rate, momentum=0.9)
# Learning rate scheduler
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

# Training function
def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('-' * 30)
        print('Epoch {}/{}'.format(epoch+1, num_epochs))

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

            running_loss = 0.0
            running_corrects = 0

            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = 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)

            if phase == 'train':
                scheduler.step()

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))

            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        print()

    time_elapsed = time.time() - since
    print('Training completed in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
    print('Best validation accuracy: {:4f}'.format(best_acc))

    model.load_state_dict(best_model_wts)
    return model

# Train the model
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=num_epochs)

# Testing function
def test_model(model, dataloader):
    model.eval()
    running_corrects = 0

    with torch.no_grad():
        for inputs, labels in dataloader:
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)
            running_corrects += torch.sum(preds == labels.data)

    test_acc = running_corrects.double() / dataset_sizes['test']
    print('Test accuracy: {:.4f}'.format(test_acc))

test_model(model_ft, dataloaders['test'])