import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor


# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))


def gen_data():
    # Download training data from open datasets.
    training_data = datasets.FashionMNIST(
        root="data",
        train=True,
        download=True,
        transform=ToTensor(),
    )

    # Download test data from open datasets.
    test_data = datasets.FashionMNIST(
        root="data",
        train=False,
        download=True,
        transform=ToTensor(),
    )
    return training_data, test_data


# Define model
class NeuralNetwork(nn.Module):
    def __init__(self, in_features, out_features):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(in_features, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, out_features)
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits


def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")


if __name__ == '__main__':
    batch_size = 64
    training_data, test_data = gen_data()
    # Create data loaders.
    train_dataloader = DataLoader(training_data, batch_size=batch_size)
    test_dataloader = DataLoader(test_data, batch_size=batch_size)

    for i, (X, y) in enumerate(test_dataloader):
        print("{}, Shape of X [N, C, H, W]: {}, y: {}".format(i, X.shape, y.shape))
        break

    model = NeuralNetwork(28*28, 10).to(device)
    print(model)
    criterion = nn.CrossEntropyLoss()
    opt = torch.optim.SGD(model.parameters(), lr=1e-3)

    n_epochs = 10

    for epoch in range(n_epochs):
        for i, (x_batch, y_batch) in enumerate(train_dataloader):
            opt.zero_grad()
            preds = model(x_batch)
            loss = criterion(preds, y_batch)
            loss.backward()
            opt.step()
            if (i+1) % 100 == 0:
                print('Train Loss: {}({}/{}): {}'.format(epoch, i, len(train_dataloader), loss.data))

        test(test_dataloader, model, criterion)