PyTorch

Common errors

Warnings

Install

Install compatibility stale last tested: 2026-05-12

Imports

• torch.load
  wrong

  model.load_state_dict(torch.load('model.pt'))  # raises UnpicklingError in 2.6+ — weights_only now defaults to True

  correct

  # For trusted checkpoints (your own models):
  model.load_state_dict(torch.load('model.pt', weights_only=True))
  
  # For checkpoints with non-tensor objects (optimizer states, custom classes):
  checkpoint = torch.load('checkpoint.pt', weights_only=False)  # only for trusted files

  torch.load weights_only parameter flipped from False to True default in 2.6. All existing torch.load() calls without explicit weights_only= raise UnpicklingError if the checkpoint contains non-tensor objects.

• device
  wrong

  model = MyModel().cuda()  # crashes on CPU-only machines with no CUDA
  tensor = tensor.cuda()

  correct

  device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
  model = MyModel().to(device)
  tensor = tensor.to(device)

  Always use .to(device) with a device variable rather than hardcoding .cuda(). .cuda() raises RuntimeError on machines without CUDA.

Quickstart stale last tested: 2026-04-23

Standard training loop and inference pattern. Always use model.eval() + torch.no_grad() for inference.

import torch
import torch.nn as nn

# Device setup
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Simple model
model = nn.Sequential(
    nn.Linear(10, 64),
    nn.ReLU(),
    nn.Linear(64, 1)
).to(device)

# Training step
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
loss_fn = nn.MSELoss()

model.train()
for x, y in dataloader:
    x, y = x.to(device), y.to(device)
    optimizer.zero_grad()
    loss = loss_fn(model(x), y)
    loss.backward()
    optimizer.step()

# Inference
model.eval()
with torch.no_grad():
    predictions = model(test_x.to(device))

# Save / load
torch.save(model.state_dict(), 'model.pt')
model.load_state_dict(torch.load('model.pt', weights_only=True))