import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torchvision.transforms import ToTensor, Lambda, Resize
# torch.backends.cudnn.benchmark=True

device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))


training_data = datasets.FashionMNIST(
    root=".\\fasionmnist",
    train=True,
    download=True,
    # transform=ToTensor(),
    transform=transforms.Compose([
        Resize((227, 227)),
        ToTensor()
    ])
)

test_data = datasets.FashionMNIST(
    root=".\\fasionmnist",
    train=False,
    download=True,
    # transform=ToTensor(),
    transform=transforms.Compose([
        Resize((227, 227)),
        ToTensor()
    ])
)

train_dataloader = DataLoader(training_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.conv2d_relu_stack = nn.Sequential(
            nn.Conv2d(1, 96, kernel_size = 11, stride=4, padding=1), nn.ReLU(),
            nn.MaxPool2d(kernel_size = 3, stride=2),
            nn.Conv2d(96, 256, kernel_size = 5, padding=2), nn.ReLU(),
            nn.MaxPool2d(kernel_size = 3, stride=2),
            nn.Conv2d(256, 384, kernel_size = 3, padding=1), nn.ReLU(),
            nn.Conv2d(384, 384, kernel_size = 3, padding=1), nn.ReLU(),
            nn.Conv2d(384, 256, kernel_size = 3, padding=1), nn.ReLU(),
            nn.MaxPool2d(kernel_size = 3, stride=2),
            nn.Flatten(),
            nn.Linear(9216, 4096), nn.ReLU(), nn.Dropout(p=0.5),
            nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(p=0.5),
            nn.Linear(4096, 10)
        )

    def forward(self, x):
        logits = self.conv2d_relu_stack(x)
        return logits

model = NeuralNetwork().to(device)

learning_rate = 1e-3
batch_size = 64
epochs = 5

# Initialize the loss function
loss_fn = nn.CrossEntropyLoss()

optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)
        # Compute prediction and loss
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # if batch % 100 == 0:
        #     loss, current = loss.item(), batch * len(X)
        #     print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test_loop(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    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")

loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

epochs = 100
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train_loop(train_dataloader, model, loss_fn, optimizer)
    test_loop(test_dataloader, model, loss_fn)
print("Done!")

torch.save(model.state_dict(), 'alexnet.model')