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

Add support for image with no annotations in RetinaNet #2800

Closed
fmassa opened this issue Oct 13, 2020 · 0 comments · Fixed by #3032
Closed

Add support for image with no annotations in RetinaNet #2800

fmassa opened this issue Oct 13, 2020 · 0 comments · Fixed by #3032
Labels
enhancement module: models topic: object detection

Comments

@fmassa
Copy link
Member

fmassa commented Oct 13, 2020

🚀 Feature

RetinaNet currently doesn't support training with images that do not have object annotations.
This has been disabled due to potential issues with distributed training.

We should enable this back.

For more context on what issues might be present, see #2784 (comment)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement module: models topic: object detection
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Support for image with no annotations in RetinaNet datumbox/vision
1 participant
@fmassa