Yiang Shi
Yiang Shi
Hi! The config for BEVFormer can refer to the baseline provided by the CVPR2023 Challenge. 1. The input query only interacts with the images and does not require self-attention. 2....
The mask_camera is used for the evaluation of Occ3D-nuS and is not needed during inference.
This infer process is the evaluation on Occ3D-nuS, so we have the mask_camera.