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

Is it possible to train a Swin-based model using bounding-box level annotations (without masks)? #154

Open
rocketsfallonrocketfalls opened this issue Mar 17, 2022 · 2 comments
Open

Is it possible to train a Swin-based model using bounding-box level annotations (without masks)? #154

rocketsfallonrocketfalls opened this issue Mar 17, 2022 · 2 comments

Comments

@rocketsfallonrocketfalls
Copy link

rocketsfallonrocketfalls commented Mar 17, 2022 •
edited

All the config files for Swin seem to be based on Mask R-CNN. So when I try to load my bounding-box level COCO annotations with the pre-existing Swin models I am getting errors e.g.:

File "pycocotools/_mask.pyx", line 292, in pycocotools._mask.frPyObjects
IndexError: list index out of range
@stevengnow
Copy link

stevengnow commented Mar 17, 2022 •
edited

Yes i would like to deactivate the segmentation masks as well. i second this question. Please let me know if you find a solution :)

@junaidp1
Copy link

#25

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@stevengnow @rocketsfallonrocketfalls @junaidp1