my xnorm in 'cfp_fp' is too big

[qiangcraft]

Hello, when I train vargfacenet with arcface, the problem always exists. The value of xnorm is very big and accuracy is very low in 'cfp_fp'. But in others validation datasets, it is normal. Could you help me? Thanks a lot. My command line is below:

python -u train.py --network vargfacenet --loss arcface --dataset retina --lr 0.01

The Xavier method is below:

initializer = mx.init.Xavier(rnd_type='gaussian', factor_type='out', magnitude=2)

[xiakj]

请问使用CFP-FP数据集的测试方法是什么啊？我用CFP-FP数据，使用10-fold交叉验证，效果很差。我感觉问题出在对齐部分。

[qiangcraft]

According to the source code of "verification.py", I also used 10-fold cross-validation. I solved it by cloning the repo again because I had no other idea. So maybe my problem was caused by my some dirty codes.

[xiakj]

@qiangz520 谢谢