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

Add support for soft margin variant of triplet loss #176

Closed
monatis opened this issue Aug 30, 2022 · 0 comments · Fixed by #178
Closed

Add support for soft margin variant of triplet loss #176

monatis opened this issue Aug 30, 2022 · 0 comments · Fixed by #178
Assignees

Comments

@monatis
Copy link
Contributor

monatis commented Aug 30, 2022

It's a trick to prevent early satisfaction of max(hard_positives - hard_negatives + margin, 0) in hard triplet loss.
Instead, it does log1p(exp(hard_positives - hard_negatives)), i.e., softplus, hence the name.

@monatis monatis self-assigned this Aug 30, 2022
@monatis monatis mentioned this issue Aug 31, 2022
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 a pull request may close this issue.

1 participant