Skip to content

/ pytorch-seq2seq

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

22 Open 115 Closed
22 Open 115 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
can i get some help?thanks!
#144 opened Nov 11, 2020 by bufuchangfeng
maybe a mistake in t6
#143 opened Nov 11, 2020 by bufuchangfeng
Question about beam search using convolution and transformer
#141 opened Oct 8, 2020 by dksifoua
4
Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)
#140 opened Oct 1, 2020 by cjjjy
1
Tutorial 6: using own data, CUBLAS status alloc failed
#139 opened Sep 25, 2020 by izaskr
2
Tutorial 6: question about dimension of trg_mask and src_mask in forward() of Encoder/Decoder/EncoderLayer/DecorderLayer.
#138 opened Sep 10, 2020 by byc1234
1
Using trg[: ,;-1] during training
#136 opened Sep 4, 2020 by wajihullahbaig
4
getting different shapes for Q,K in Multihead attention values pytorch-seq2seq in DataParallel
#135 opened Sep 2, 2020 by VinACE
Model actually corrects "ground truth" (6 - Attention is All You Need).
#134 opened Sep 1, 2020 by sechegaray
1
tut 6 - when slicing the <eos> token off from trg before feeding it into the model
#133 opened Aug 26, 2020 by JaeyoonChun
4
How to matrix multiply two encoded representations?
#128 opened Aug 15, 2020 by jlim13
1
Tutorial 3 : Aligment Model not the same as the paper
#126 opened Aug 5, 2020 by xxoospring
1
I can not import bleu score.
#125 opened Aug 3, 2020 by GlazeDonuts
2
Tutorial 6: Batch inference to speed up the translation
#123 opened Jul 20, 2020 by ruathudo
3
In Tutorial 1 target sequence len is used at time of evaluation
#122 opened Jul 10, 2020 by dineshkh
1
BERT Model for Tokenization and Initialization of embedding layer waiting-reply
#114 opened May 19, 2020 by kr-sundaram
1
Tutorial 6: byte pair encoding enhancement
#106 opened May 1, 2020 by brand17
1
beam search enhancement
#93 opened Apr 3, 2020 by wangleiai
1
In the encoder. Why not use pack_padded_sequence (embedded, input_lengths) question
#91 opened Mar 30, 2020 by lightcome
3
A question about tutorial1. question
#88 opened Mar 24, 2020 by TomasAndersonFang
1
Using 6th notebook for Video captioning waiting-reply
#85 opened Mar 21, 2020 by kushalj001
5
arguments are located on different GPUs bug
#4 opened Nov 11, 2018 by SoheilZabihi
4
ProTip! Add no:assignee to see everything that’s not assigned.
You can’t perform that action at this time.