How to undersatand the weight?

wujiyang / Face_Pytorch

face recognition algorithms in pytorch framework, including arcface, cosface, sphereface and so on

Apache License 2.0

808 stars 156 forks source link

How to undersatand the weight? #41

Open taylover-pei opened 5 years ago

taylover-pei commented 5 years ago

You have done a great work!

But I have a question about the ArcFace_loss. How to understand the weigth as show bellow:

I think thay are stand for the parameters of the last fully connected layer. But I wonder how to upodate them. In your code, I think they are fixed values, are they?

Looking forward to your reply.

leon0n commented 4 years ago

I think it is equal to a Fully Connected Layer without Bias. In the training process, the optimizer parameters comprise the backbone parameters and the margin parameters (which means the self.weight). By the optimizer, the parameters self.weights will be updated