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 Owlv2; Add option to use owlvit / owlv2's image preprocessing procedure (the roi_align in current implementation processes images differently and results in distribution shifts and subpar performance) #23

Open
wants to merge 8 commits into
base: main
Choose a base branch
from

Conversation

xuanlinli17
Copy link

@xuanlinli17 xuanlinli17 commented Mar 7, 2024

  • Factor in a bug found by Fix bug with non square images #20
  • Add Owlv2
  • Add an option (no_roi_align) in the OwlPredictor class of nanoowl/owl_predictor.py to use the original owlvit / owlv2 implementation's image preprocessing procedure. From my debugging, I find that the current nanoowl repo preprocesses images differently from the original owlvit / owlv2 implementations due to the use of "roi_align". This causes the larger models (base-16, large-14) to perform subpar compared to the original owlvit / owlv2. Passing in no_roi_align=True fixes this issue.
  • Add an option (nms_threshold) to use non-maximal suppression bounding box filtering
  • Fix cv2 "image no write permission" error in drawing utils

@xuanlinli17 xuanlinli17 changed the title Add Owlv2; Add option to use original owlvit / owlv2's image preprocessing (instead of roi align as in current nanoowl) Add Owlv2; Add option to use owlvit / owlv2's image preprocessing procedure (the roi_align in current implementation processes images differently and results in distribution shifts) Mar 7, 2024
@xuanlinli17 xuanlinli17 changed the title Add Owlv2; Add option to use owlvit / owlv2's image preprocessing procedure (the roi_align in current implementation processes images differently and results in distribution shifts) Add Owlv2; Add option to use owlvit / owlv2's image preprocessing procedure (the roi_align in current implementation processes images differently and results in distribution shifts and subpar performance) Mar 7, 2024
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