Adding ciou and diou support in _box_loss()#5984
Merged
datumbox merged 4 commits intopytorch:mainfrom May 11, 2022
Merged
Conversation
oke-aditya
reviewed
May 10, 2022
zhiqwang
reviewed
May 11, 2022
24 tasks
facebook-github-bot
pushed a commit
that referenced
this pull request
May 20, 2022
Summary: * Adding ciou and diou support in `_box_loss()` * Fix linter * Addressing comments for nits Reviewed By: datumbox Differential Revision: D36413352 fbshipit-source-id: 8a53c68ff2a58966f02edae7f210c8db5240a4d2
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Related to #5983
Adding support of cIoU and dIoU loss on the private
_box_loss()used for regression. Currently this is an internal API used only by RetinaNet. I've done limited runs and seems that neither of the two losses improve performance:Hence I wont be making any changes on the
retinanet_resnet50_fpn_v2pretrained weights.