MCG-NJU/SparseOcc

About RayPQ performance

Opened this issue · 1 comments

Thank you for your great work.
I have one question. The RayPQ of the panoptic model weight is 12.73, which seems to be different from the value of 14 posted on GitHub.

We use the panoptic model weight to eval again and get the same RayPQ result as posted, maybe you can check if there's something wrong with the settings or provide more details about this question.