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
Hi! When I use examples.py for lannguage translation, an error occured in def len_filter if I use all train_datasets. But when I use part of train_datasets, it works well. Could you please tell me why?
#162
Open
Decalogue opened this issue
Sep 5, 2018
· 2 comments
Hi!
When I use examples.py for lannguage translation, an error occured in 'def len_filter' if I use all trainning datasets. But when I use part of trainning datasets, it works well. Could you please tell me why?
The AttributeError is like this:
File "train_seq2seq.py", line 81, in len_filter
return len(example.src) <= max_len and len(example.tgt) <= max_len
AttributeError: 'Example' object has no attribute 'tgt'
Thank you!
The text was updated successfully, but these errors were encountered:
@Decalogue You could pull develop and try implementing your script again. Seq2seqDataset has been introduced after #163. However things might be a little unstable as develop is pushed to weekly so I'd recommend you either create a fork or wait until the next alpha release v0.1.7.
Hi!
When I use examples.py for lannguage translation, an error occured in 'def len_filter' if I use all trainning datasets. But when I use part of trainning datasets, it works well. Could you please tell me why?
The AttributeError is like this:
File "train_seq2seq.py", line 81, in len_filter
return len(example.src) <= max_len and len(example.tgt) <= max_len
AttributeError: 'Example' object has no attribute 'tgt'
Thank you!
The text was updated successfully, but these errors were encountered: