1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
| 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(), )
batch_size = 64
train_dataloader = DataLoader(training_data, batch_size=batch_size) test_dataloader = DataLoader(test_data, batch_size=batch_size)
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(f"Using {device} 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.ReLU(), nn.Linear(512, 512), nn.ReLU(), nn.Linear(512, 10) )
def forward(self, x): x = self.flatten(x) logits = self.linear_relu_stack(x) return logits
model = NeuralNetwork().to(device) print(model)
loss_fn = nn.CrossEntropyLoss() optimizer = torch.optim.SGD(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)
loss.backward() optimizer.step() optimizer.zero_grad()
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 State to model.pth")
model = NeuralNetwork().to(device) 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(): x = x.to(device) pred = model(x) predicted, actual = classes[pred[0].argmax(0)], classes[y] print(f'Predicted: "{predicted}", Actual: "{actual}"')
|