You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I found this bug when running the basic script, example/sample.py:
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected object of type torch.cuda.LongTensor but found type torch.LongTensor for argument #3 'index'
It seems to be a wrong type of tensor on GPU.
The text was updated successfully, but these errors were encountered:
Heads up, I'm getting the same errors after a fresh clone. I've been manually adding if torch.cuda.is_available(): VARIABLE.cuda() entries to get around it temporarily.
I found this bug when running the basic script, example/sample.py:
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected object of type torch.cuda.LongTensor but found type torch.LongTensor for argument #3 'index'
It seems to be a wrong type of tensor on GPU.
The text was updated successfully, but these errors were encountered: