Error for cuda and cpu

[lucasjinreal]

/pytorch-seq2seq/seq2seq/models/EncoderRNN.py", line 68, in forward
    embedded = self.embedding(input_var)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 479, in __call__
    result = self.forward(*input, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/sparse.py", line 113, in forward
    self.norm_type, self.scale_grad_by_freq, self.sparse)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py", line 1283, in embedding
    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected object of backend CUDA but got backend CPU for argument #3 'index'

[pskrunner14]

@jinfagang could you try running your code with develop branch?

[Huijun-Cui]

bug bug bug !!!!!!!!!!!!!!!!!!!!!!!!!!!! waste my time!!!!!!!!!!!

[lucasjinreal]

@Hujun-Cui I think this repo is not active maintained now.

[pskrunner14]

@jinfagang this has been a recurring issue, however the fix has already been made on the develop branch. Will update on master soon. Please see #180 for a simple workaround.

[v587su]

The wrong code is at line 75 of supervised_trainer.py and line 38 of evaluator.py. I change them to device = torch.device('cuda:0') if torch.cuda.is_available() else -1 and CUDA is available now.

[rain1024]

I think this should be merged in master now.

[Hexagram-King]

The wrong code is at line 75 of supervised_trainer.py and line 38 of evaluator.py. I change them to device = torch.device('cuda:0') if torch.cuda.is_available() else -1 and CUDA is available now.

Except the two files, is there any other file need to fix? After fix the two files, the code still be incorrect...

[isekulic]

The wrong code is at line 75 of supervised_trainer.py and line 38 of evaluator.py. I change them to device = torch.device('cuda:0') if torch.cuda.is_available() else -1 and CUDA is available now.

Except the two files, is there any other file need to fix? After fix the two files, the code still be incorrect...

No, but you need to re-install the package after you do these corrections. Running python setup.py install again helped in my case.