search

WangYueFt / dgcnn

MIT License
1.64k stars 422 forks source link

Why bias=None in conv2d? #37

Closed kxhit closed 5 years ago

kxhit commented 5 years ago

Hi! I have some small questions about the code.

  1. I noticed that bias is set to None in both PointNet and dgcnn. I'm curious why we do that? I can't find the explanation in these papers.
  2. Do we need to apply batch normalization on the input (before conv1)?

Thanks a lot if someone could help me!!!

WangYueFt commented 5 years ago

Because we use batchnorm, whether using the bias won't make any difference.