Skip to content
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

when run predit error #2

Open
457138317 opened this issue Dec 17, 2018 · 4 comments
Open

when run predit error #2

457138317 opened this issue Dec 17, 2018 · 4 comments

Comments

@457138317
Copy link

Hi, thanks u for your awesome work! however when i run predict.py, there is no beam_sample method in seq2seq, can u add the method in the seq2seq.py?

@shumingma
Copy link
Contributor

Hi, thanks for reporting the issue. We are working on that. The codes will be updated once it is done.

@457138317
Copy link
Author

Hi, thanks for reporting the issue. We are working on that. The codes will be updated once it is done.

thanks. however i also want to know how can i reproduce the result that you reported in the paper, just follow the default config is enough?

@457138317
Copy link
Author

      Hi, thanks for reporting the issue. We are working on that. The codes will be updated once it is done.

hi, dear shumingma. can you offer your pretrain model ? i want to reproduce the result in your paper. however, i just only can achieve 48.2 belu score on pwkp corpus for your default config. thank you very much

@shumingma
Copy link
Contributor

      Hi, thanks for reporting the issue. We are working on that. The codes will be updated once it is done.

hi, dear shumingma. can you offer your pretrain model ? i want to reproduce the result in your paper. however, i just only can achieve 48.2 belu score on pwkp corpus for your default config. thank you very much

Of course we are happy to release the pretrained model. But we have found some incompatible between the saved checkpoint files we have and the current version of the released codes. We are trying to deal with this problem by updating the version of codes or retrain a new model. It is expected to be done in a few days. Thanks for reporting this issue!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants