BEVFormer
BEVFormer copied to clipboard
About the VoVnet-99 checkpoint and config
Hi, thanks for the great work!
I wonder if you could release the VoVnet-99 version checkpoint and config, so that the test set results can be reproduced? Right now there is code for vovnet.py, but really no config or experiment use that code.
Also, I wonder what pre-trained checkpoint for VoVnet-99 did you use? Was it first pre-trained on the COCO dataset for 2D Detection, and then pre-trained on the DDAM-15M dataset for depth prediction? Did you freeze any layer/stage in VoVnet-99 when training for 3D Detection?
Thanks a lot!
How did you replace ResNet-101 with VoVNet? I'm encountering some issues now
This is the code I modified for bevformer_small.py