Feiyan

The ratio of pos:part:neg that you used is about 1:1:2, why? The paper said the ratio is 1:1:3

Angles regression is different in the paper and the code!

2

In the paper, angles regression is used by equation (6c), I find the tan() is used! While sin() is used in the code! Why? And which way is the best?

Question about file small_crops.txt.

2

THow to generate file small_ crops.txt？

Question about amsoftmax.

1

`class ArcMarginProduct(nn.Module): def __init__(self, in_feature=128, out_feature=10575, s=32.0, m=0.50, easy_margin=False): super(ArcMarginProduct, self).__init__() self.in_feature = in_feature self.out_feature = out_feature self.s = s self.m = m self.weight = Parameter(torch.Tensor(out_feature, in_feature)) nn.init.xavier_uniform_(self.weight) self.easy_margin =...

The results of multi task training are worse.

1

The accuracy of multi task training on celebboof is as follows: ` accuracy on test data = 0.946 AUC = 0.998 EER = 2.45 apcer = 0.55 bpcer = 7.39...

Question about Faceswap.

1

I find that you did not use the DAMDNet model in Demo2.py and used 'candide.npz'. Why?

Could you please release the test code of fddb or tell some hyperparameters?