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

why the gradient become very few after neuralsort ? #12

Open
buptzzl opened this issue Sep 30, 2021 · 0 comments
Open

why the gradient become very few after neuralsort ? #12

buptzzl opened this issue Sep 30, 2021 · 0 comments

Comments

@buptzzl
Copy link

buptzzl commented Sep 30, 2021

I try to do SGD optimizer after neuralsort operation, but after this operation, the gradient backup to dense layer become very few, like for 0.23 to -1.12376988e-07 . why ? how to enlarge the gradient.
Thanks very much!
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
1 participant
@buptzzl