Clarification about multi-bin classification loss?

[sauravshanu]

Hi,

Thanks for providing the code. I have a question about the multi-bin classification loss. In the Mono3D paper, it is mentioned that the cross-entropy loss is used for the multi-bin classification of width, height, and length.

However, looking at the code in detection_3d_head.py, I find that it is being used only for angle alpha. Am I understanding the code wrong? Can you please clarify that?

Thank you

[Owen-Liuyuxuan]

When I try to open-source the code, I made it easier to adapt to other datasets with more classes, so the multi-bin classification for rotation is skipped.