RuntimeError: Expected object of backend CPU but got backend CUDA for argument #2 'other'

[fabrahman]

Hello,

Thank you for sharing your code.

I tried running the code (train.py) on a dataset (both source and target are English) and I am getting the following error in Batch.py.

loading spacy tokenizers...
creating dataset and iterator...
The `device` argument should be set by using `torch.device` or passing a string as an argument. This behavior will be deprecated soon and currently defaults to cpu.
training model...
cudam: epoch 1 [                    ]  0%  loss = ...
Traceback (most recent call last):
  File "train.py", line 183, in <module>
    main()
  File "train.py", line 111, in main
    train_model(model, opt)
  File "train.py", line 34, in train_model
    src_mask, trg_mask = create_masks(src, trg_input, opt)
  File "/home/hannahbrahman/ROCstories/Transformer/Batch.py", line 26, in create_masks
    trg_mask = trg_mask & np_mask
RuntimeError: Expected object of backend CPU but got backend CUDA for argument #2 'other'

I tried to add device= torch.device('cuda' if torch.cuda.is_available() else 'cpu') and np_mask.to(device) but still getting the same error. I git cloned your repo on my own machine and tried running train.py. My pytorch version is: 1.0.0.dev20181105

[fmobrj]

Hello. Great project.

I'm having the same issue as Hannabrahman. Exactly the same message.

I've tried pytorch 4.0 and 4.1 and cant get rid of this message.

[fabrahman]

@fmobrj Hi, try adding .to('cuda') or .cuda() at the end lines 31 , 32 of train.py. that is:

src = batch.src.transpose(0,1).to('cuda') trg = batch.trg.transpose(0,1).to('cuda')

That worked for me. Good luck

[fmobrj]

Hi, Hannabrahman! Thank you very much! Now it is working fine.

I am evaluating some Transformer projects, so I can fine tune my own, to my needs. It seems, by the folder structure, that most of them are forks from the OpenNmt project,

Best regards!