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

Use non-ragged outputs in MultiClassNMS #2030

Merged
merged 2 commits into from
Aug 16, 2023
Merged

Conversation

ianstenbit
Copy link
Contributor

Using Ragged outputs that weren't subsequently padded was causing issues in the PyCOCOCallback, and we shouldn't silently default to Ragged anywhere.

Using Ragged outputs that weren't subsequently padded was causing issues in the PyCOCOCallback, and we shouldn't silently default to Ragged anywhere.
@ianstenbit
Copy link
Contributor Author

/gcbrun

@ianstenbit
Copy link
Contributor Author

Fixes #2014

@ianstenbit ianstenbit merged commit db57e1d into master Aug 16, 2023
16 checks passed
@ianstenbit ianstenbit deleted the ianstenbit-patch-1 branch August 16, 2023 16:17
@sampathweb
Copy link
Collaborator

LGTM. Thanks for fixing this issue with COCO Callback.

ghost pushed a commit to y-vectorfield/keras-cv that referenced this pull request Nov 16, 2023
* Use non-ragged outputs in MultiClassNMS

Using Ragged outputs that weren't subsequently padded was causing issues in the PyCOCOCallback, and we shouldn't silently default to Ragged anywhere.

* Update multi_class_non_max_suppression_test.py
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