I have move the model and the data to the same device, but I still get the following errors.
Traceback (most recent call last):
File "train.py", line 418, in <module>
main(args)
File "train.py", line 298, in main
train_loss, train_acc1, train_acc5 = train_one_epoch(model, criterion, optimizer, data_loader, device, epoch,
File "train.py", line 69, in train_one_epoch
scaler.scale(loss).backward()
File "/home/lyd/.conda/envs/lyd/lib/python3.8/site-packages/torch/_tensor.py", line 363, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/home/lyd/.conda/envs/lyd/lib/python3.8/site-packages/torch/autograd/__init__.py", line 173, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:1! (when checking argument for argument weight in method wrapper__native_batch_norm_backward)