llf1234

some confusion about Content Encoder

1

thanks for your excellent work？ why adding gaussian noise layer in E_encoder is really confused me？ hope for your apply

speak first,i appreciate your excellent work very much. but what confuses me a lot is why you initialize the last fc layer(bias term) in insightface.py using xavier_init() while in resface.py...

the color of generated pic is not consistent with orginal

7

thanks a lot，recently i train a model with your provided code and data，i find the color of generated eyes is not always consistent with the original input（test on other pic...

some confuse

2

在一些深度哈希里面，都是将cifar10分成trainset-5000，queryset-1000，database-（54000）然后仅仅在trainset-5000上训练。 在您的工作做，是把cifar10分成queryset/database 然后在database上训练，并得到特征提取网络和database的二值化表示，我想问的是假如我在实际应用中换了database，或者database中没有相应的标注。这样应该大大限制了该工作的应用吧

about feature renorm

1

hi ~ i find you used norm feature in backbone , can you explain this op? And compared to un-norm feature ，is it usefully code: renorm(2,0,1e-5).mul(1e-5)