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.

Sign up for GitHub

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

Jump to bottom

loss #24

Closed
neversettle-tech opened this issue Sep 5, 2021 · 7 comments
Closed

loss #24

neversettle-tech opened this issue Sep 5, 2021 · 7 comments

Comments

@neversettle-tech
Copy link

Is there only MSE Loss in the code, but no ISMM Loss？
Will it affect my training？
@dk-liang
Copy link
Owner

dk-liang commented Sep 5, 2021

No, it can train with MSE loss.

@neversettle-tech
Copy link
Author

However, using only one Loss let me feel that the training effect is not very good.
Can you upload the complete code？

@dk-liang
Copy link
Owner

dk-liang commented Sep 6, 2021

However, using only one Loss let me feel that the training effect is not very good.
Can you upload the complete code？

This work is under review, we will release the code when the review is completed.

@neversettle-tech
Copy link
Author

So, when will it be released？

@neversettle-tech
Copy link
Author

When will the code finish the reviewed?

@dk-liang
Copy link
Owner

dk-liang commented Sep 6, 2021

When will the code finish the reviewed?

Depending on the reviewers.

@dk-liang
Copy link
Owner

dk-liang commented Sep 8, 2021

The paper is under review instead of the code.

@dk-liang dk-liang closed this as completed Sep 8, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@dk-liang @neversettle-tech