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

[onert-micro] Fix grad of Sparse Cross Entropy Loss #14119

Merged
merged 1 commit into from
Oct 10, 2024

Conversation

chunseoklee
Copy link
Contributor

  • Fix wrong sparse CCE loss grad computation

ONE-DCO-1.0-Signed-off-by: Chunseok Lee [email protected]

- Fix wrong sparse CCE loss grad computation

ONE-DCO-1.0-Signed-off-by: Chunseok Lee <[email protected]>
@chunseoklee
Copy link
Contributor Author

@ljwoo94 I didnt test #13637 with this PR :)

Copy link
Contributor

@ljwoo94 ljwoo94 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM.
This modification makes similar shape of logic compare to that of CrossEntropy backward propagation.

I tested with testcase in #13637 and gained same accuracy result.

@chunseoklee chunseoklee merged commit c507999 into Samsung:master Oct 10, 2024
4 checks passed
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

Successfully merging this pull request may close these issues.

2 participants