Created
July 2, 2023 13:24
-
-
Save hopezh/1bf785a2e257e7f22256586b34218d64 to your computer and use it in GitHub Desktop.
PyTorch QuickStart Example Code
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch | |
from torch import nn | |
from torch.utils.data import DataLoader | |
from torchvision import datasets | |
from torchvision.transforms import ToTensor | |
print("PyTorch version:", torch.__version__) | |
# ------------------------------------------------------------------------------ | |
# download training data | |
training_data = datasets.FashionMNIST( | |
root="data", | |
train=True, | |
download=True, | |
transform=ToTensor(), | |
) | |
# download test data | |
test_data = datasets.FashionMNIST( | |
root="data", | |
train=False, | |
download=True, | |
transform=ToTensor(), | |
) | |
# ------------------------------------------------------------------------------ | |
batch_size = 64 | |
# create data loaders | |
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 | |
# ------------------------------------------------------------------------------ | |
# get cpu, gpu or mps device for training | |
device = ( | |
"cuda" | |
if torch.cuda.is_available() | |
else "mps" | |
if torch.backends.mps.is_available() | |
else "cpu" | |
) | |
print(f"Using {device} device") | |
# define model | |
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:") | |
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) | |
# compute prediction error | |
pred = model(X) | |
loss = loss_fn(pred, y) | |
# backpropagation | |
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}"') | |
# ------------------------------------------------------------------------------ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment