Vincent Nguyen

@vikrant97 your request is unclear to me. each feature must have a constant vec size. eg: if you have two features F1 and F2,then each example must have the same...

ok, then what is the issue of setting for instance emb_size 500 feat_vec_size 6, hidden 512 and if you have 2 features, it should work fine it is not a...

ok I see, what you are asking is in fact a duplicate of this: https://github.com/OpenNMT/OpenNMT-py/issues/344 @bpopeters since you started to work onit, can you give him some pointers so that...

If you want to discuss some of your code, please open e [WIP] PR and then we cansse what is going right and wrong. Without knowing what you have done,...

@Henry-E Just trying to document a bit this, when you have one extra feature of size 12 src_word_vec_size = 500 feat_vec_size = 12 rnn_size = 512 tgt_word_vec_size = 512 share_embeddings=...

@pltrdy can you please have a look ?

might be a beam size issue, try with 15.

it's annoying. Do you have time to download one of the summarization pretrained models ? (an LSTM one)

@sebastianGehrmann in case you understand what is happening, welcome.

I think this is done on purpose, but @pltrdy may explain better.