search

zehuichen123 / BEVDistill

[ICLR 2023] BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection
117 stars 6 forks source link

How to enable CBGS? #5

Open sunnyHelen opened 1 year ago

sunnyHelen commented 1 year ago

Hi, I noticed there are some results obtained by using CBGS in your paper. Could you please tell me how to enable CBGS in your code?

zehuichen123 commented 1 year ago

Hi, the CBGS was adopted on the BEVDepth-based model following the implementation from the official BEVDet (https://github.com/HuangJunJie2017/BEVDet/blob/f71858d02eb0fbd09860150ade67558d7984b1be/configs/bevdet/bevdet-r50-4d-depth-cbgs.py#L284). For BEVFormer, we simply follow its original implementation, which seems no CBGS is adopted.