Jinyu Li

swig polyiou.i

1

swig -c++ -python polyiou.i polyiou.h:1: Error: Unterminated character constant

I observed that segmentation prediction label must be between 1-16, but you predict 0-16 in nuscenes yaml. So how do you process label 0?

I'm struggling with creating virtual environment for PillarNet. I'd appreciate if you could provide the list of all libraries.

Inference Speed on Waymo val set

2

Thanks for your excellent work and I'm wondering if you have ever tested inference speed on Waymo val set?

according to your paper, lr is set to 0.12. Is it too large? And what is the batch size with lr 0.12?