Parag Jain

I am also facing the same issue. @kno10 Can you please give some details on how to use your quick fix until this is fixed? Also, digits+(no space)+dot rule seems...

Getting the same error while using nn.Embedding. During init I do: self.embedding = nn.Embedding(output_size, hidden_size) And during the forward pass: word_embedded = self.embedding(word_input) I am getting similar error: TypeError: torch.index_select...

I was able to fix it, word_input was not converted to cuda in this case. My bad. Thanks for the help.

I am also facing a similar issue. While training BLEU and sample predictions are much better as compared to inference.

Looks like those are from training data so expected them to be better. https://github.com/google/seq2seq/blob/93c600a708a3fdd0473c3b3ce64122f3150bc4ef/seq2seq/training/hooks.py#L141 In that case there is no issue.

Hi,.. Were you able to look at it? Is there any alternative? Thanks

No