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

torch version #2

Open
linhanxiao opened this issue Sep 28, 2017 · 2 comments
Open

torch version #2

linhanxiao opened this issue Sep 28, 2017 · 2 comments

Comments

@linhanxiao
Copy link

thank you for Implementation of A Structured Self-attentive Sentence Embedding,Do you have the torch
implementation version

@yufengm
Copy link
Owner

yufengm commented Sep 29, 2017

I'm sorry that I just implement it in pytorch.

@linhanxiao
Copy link
Author

Can I ask you about the torch implementation version, in your pytorch implementation,the penal was directly added to entropyloss and loss.backward(),in torch implementation,what should i do to implement
the similar function,should icreate a new class inherited from nn.Criterion to implement it?

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