Why do a_p and a_n use .detach()?

[Zhisheng Zhong]

Hi, thanks for your code!

I wonder why a_p and a_n use .detach() here?

CircleLoss/circle_loss.py

Line 28 in d002ecd

 ap = torch.clamp_min(- sp.detach() + 1 + self.m, min=0.) 

As Eq. (9) and (10) in the original paper, it seems a_p and a_n are involved in the gradient computation.

Hope to get your answer, thanks!