jiangxuehan

@mfs6174 , have you reproduced the result on LFW or Megaface? I have trained the model on CASIA and tested on LFW ,but it didn't work well (EER~96.5%).

Hi, @mfs6174 @chichan01 , to mfs6174 : I used the paper author's code. Further discussions after you finish experiments will be appreciated. (By the way,your optimized code is correct and...

@chichan01 : Could you please send your train log files to me(both 98.47 and NAN )? I want to compare loss curves and hope it can provide some useful information....

Hi @mfs6174 @chichan01 As mfs6174 metioned, center = center - lr_mult_lr_d(center), so alpha = lr_mult_lr.With lr decrease from 0.1 to 0.01/0.001, we should set lr_mult to 5/50/500 theoretically. Besides ,...

@Tongcheng I have run models in this repo, for k=12 and L=100, the accuracy on cifar10+ is 94.8%, but it should be 95.5% according to the paper. Looking forward your...

@Tongcheng. Thanks for your reply. Using ImageDataLayer with shuffle option can get the same result(95.2%) with your modified DataLayer. Do you think if there are some other differences between Torch...

@sciencefans could you tell us which dataset was used for Megaface? The 76.57% result was indicated with "small" dataset, however in section 6.2 of your paper, there are 3M images...