mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 21:14:14 +08:00
f3fce597e9
See https://github.com/pytorch/pytorch/pull/129751#issue-2380881501. Most changes are auto-generated by linter. You can review these PRs via: ```bash git diff --ignore-all-space --ignore-blank-lines HEAD~1 ``` Pull Request resolved: https://github.com/pytorch/pytorch/pull/129769 Approved by: https://github.com/ezyang
94 lines
2.7 KiB
Python
94 lines
2.7 KiB
Python
# mypy: ignore-errors
|
|
|
|
import os
|
|
|
|
from torchvision import datasets, transforms
|
|
|
|
import torch
|
|
import torch._lazy
|
|
import torch._lazy.metrics
|
|
import torch._lazy.ts_backend
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
import torch.optim as optim
|
|
from torch.optim.lr_scheduler import StepLR
|
|
|
|
|
|
torch._lazy.ts_backend.init()
|
|
|
|
|
|
class Net(nn.Module):
|
|
def __init__(self) -> None:
|
|
super().__init__()
|
|
self.conv1 = nn.Conv2d(1, 32, 3, 1)
|
|
self.conv2 = nn.Conv2d(32, 64, 3, 1)
|
|
self.dropout1 = nn.Dropout(0.25)
|
|
self.dropout2 = nn.Dropout(0.5)
|
|
self.fc1 = nn.Linear(9216, 128)
|
|
self.fc2 = nn.Linear(128, 10)
|
|
|
|
def forward(self, x):
|
|
x = self.conv1(x)
|
|
x = F.relu(x)
|
|
x = self.conv2(x)
|
|
x = F.relu(x)
|
|
x = F.max_pool2d(x, 2)
|
|
x = self.dropout1(x)
|
|
x = torch.flatten(x, 1)
|
|
x = self.fc1(x)
|
|
x = F.relu(x)
|
|
x = self.dropout2(x)
|
|
x = self.fc2(x)
|
|
output = F.log_softmax(x, dim=1)
|
|
return output
|
|
|
|
|
|
def train(log_interval, model, device, train_loader, optimizer, epoch):
|
|
model.train()
|
|
for batch_idx, (data, target) in enumerate(train_loader):
|
|
data, target = data.to(device), target.to(device)
|
|
optimizer.zero_grad(set_to_none=True)
|
|
output = model(data)
|
|
loss = F.nll_loss(output, target)
|
|
loss.backward()
|
|
optimizer.step()
|
|
torch._lazy.mark_step()
|
|
|
|
if batch_idx % log_interval == 0:
|
|
print(
|
|
f"Train Epoch: {epoch} "
|
|
f"[{batch_idx * len(data)}/{len(train_loader.dataset)} ({100.0 * batch_idx / len(train_loader):.0f}%)]"
|
|
f"\tLoss: {loss.item():.6f}"
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
bsz = 64
|
|
device = "lazy"
|
|
epochs = 14
|
|
log_interval = 10
|
|
lr = 1
|
|
gamma = 0.7
|
|
train_kwargs = {"batch_size": bsz}
|
|
# if we want to use CUDA
|
|
if "LTC_TS_CUDA" in os.environ:
|
|
cuda_kwargs = {
|
|
"num_workers": 1,
|
|
"pin_memory": True,
|
|
"shuffle": True,
|
|
"batch_size": bsz,
|
|
}
|
|
train_kwargs.update(cuda_kwargs)
|
|
|
|
transform = transforms.Compose(
|
|
[transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
|
|
)
|
|
dataset1 = datasets.MNIST("./data", train=True, download=True, transform=transform)
|
|
train_loader = torch.utils.data.DataLoader(dataset1, **train_kwargs)
|
|
model = Net().to(device)
|
|
optimizer = optim.Adadelta(model.parameters(), lr=lr)
|
|
scheduler = StepLR(optimizer, step_size=1, gamma=gamma)
|
|
for epoch in range(1, epochs + 1):
|
|
train(log_interval, model, device, train_loader, optimizer, epoch)
|
|
scheduler.step()
|