Open taylover-pei opened 5 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
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.