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

Question about inference #15

Open
SY-Xuan opened this issue Jul 15, 2022 · 2 comments
Open

Question about inference #15

SY-Xuan opened this issue Jul 15, 2022 · 2 comments

Comments

@SY-Xuan
Copy link

SY-Xuan commented Jul 15, 2022

During inference, the token (5-th) that is corresponded to the object class may be classified to the coordinates. In the other hand, the token that is corresponded to the coordinates still has chance to be classified to the class of the object. How to deal with such situation? Thanks a lot.

@chentingpc
Copy link
Collaborator

you can offset logits before sampling if you want to disable certain predictions (e.g. set -1e9 for logits that correspond to class/coordinates). but we find that just free sampling is fine.

@SY-Xuan
Copy link
Author

SY-Xuan commented Jul 17, 2022

Thanks for your kindly replying!

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