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

During inference, why there are requirements to provide the valid(joint valid) information from annotation? #4

Closed
warmheartHoward opened this issue Jun 7, 2024 · 1 comment

Comments

@warmheartHoward
Copy link

I try to apply your weight to my own stereo scenario, but during the evaluate process, i found out there are requirements to provide the joints valid information when doing the merge for two predictions. but the valid information come from the annotations.
image
why?

@MickeyLLG
Copy link
Collaborator

Yes, we use valid label from the annotation, which indiactes the visibility of each joint. Such usage is actually common in existing studies.
However, it is also okay to set the valid information all-one matrices.

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

No branches or pull requests

2 participants