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

training_data = datasets.FashionMNIST(
	root="data",
	train=True,
	download=True,
	transform=ToTensor(),
)

test_data = datasets.FashionMNIST(
	root="data",
	train=False,
	download=True,
	transform=ToTensor(),
)

print(training_data)
print(test_data)
batch_size=8192
train_dataloader = DataLoader(training_data, batch_size=batch_size, shuffle=True)
test_dataloader = DataLoader(test_data, batch_size=batch_size, shuffle=True)

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

device = (
	"cuda" if torch.cuda.is_available()
			else "mps" if torch.backends.mps.is_available()
			else "cpu"
)
print(device)

class NeuralNetwork(nn.Module):
	def __init__(self):
		super().__init__()
		self.flatten = nn.Flatten()
		self.linear_relu_stack = nn.Sequential(
			nn.Linear(28 * 28, 512),
			nn.BatchNorm1d(512),
			nn.ReLU(),
			nn.Linear(512, 512),
			nn.BatchNorm1d(512),
			nn.ReLU(),
			nn.Linear(512, 512),
			nn.BatchNorm1d(512),
			nn.ReLU(),
			nn.Linear(512, 512),
			nn.BatchNorm1d(512),
			nn.ReLU(),
			nn.Linear(512, 512),
			nn.BatchNorm1d(512),
			nn.ReLU(),
			nn.Linear(512, 10)
		)
	
	def forward(self, x):
		# torch.Size([64, 1, 28, 28])
		# torch.Size([64, 784])
		# torch.Size([64, 10])
		# print("=====")
		#print(x.shape)
		x = self.flatten(x)
		#print(x.shape)
		logits = self.linear_relu_stack(x)
		#print(logits.shape)
		return logits

model = NeuralNetwork().to(device)
print(model)

loss_fn = nn.CrossEntropyLoss().to(device)
optimizer = torch.optim.AdamW(model.parameters(), lr=1e-3)

def train(dataloader, model, loss_fn, optimizer):
	size = len(dataloader.dataset)
	model.train()
	for batch, (X, y) in enumerate(dataloader):
		X, y = X.to(device), y.to(device)
		pred = model(X)
		loss = loss_fn(pred, y)
	
		optimizer.zero_grad()
		loss.backward()
		optimizer.step()
	
		if batch % 100 == 0:
			loss, current = loss.item(), (batch + 1) * len(X)
			print(f"loss: {loss:>7f} [{current:>5d}/{size:>5d}]")

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")

epochs = 5
for t in range(epochs):
	print(f"Epoch {t+1}\n---------------------")
	train(train_dataloader, model, loss_fn, optimizer)
	test(test_dataloader, model, loss_fn)

print("Done!")

torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model Sate to model.pth")

model = NeuralNetwork()
model.load_state_dict(torch.load("model.pth"))

classes = [
	"T-shirt/top",
	"Trouser",
	"Pullover",
	"Dress",
	"Coat",
	"Sandal",
	"Shirt",
	"Sneaker",
	"Bag",
	"Ankle Boot",
]

model.eval()
x, y = test_data[0][0], test_data[0][1]
with torch.no_grad():
	pred = model(x)
	predicted, actual = classes[pred[0].argmax(0)], classes[y]
	print(f'Predicted: "{predicted}", Actual: "{actual}"')