haolinlyou

Results 5 comments of haolinlyou

> set lr = 0.1 at the begining. OK Thank you for your reply. By the way, i foud the loss is nearly 0.004 when training in epoch 30.

我也遇到这种情况了,请问解决了么

我实在ms1m上训练的,训练的时候有个bug,导致了之前loss的计算有问题。后来我改了下,现在是loss在20左右就开始不下降了,agedb30的准确率为92%左右,同时batch_acc还是0,现在也不知道该咋弄了

> > 我实在ms1m上训练的,训练的时候有个bug,导致了之前loss的计算有问题。后来我改了下,现在是loss在20左右就开始不下降了,agedb30的准确率为92%左右,同时batch_acc还是0,现在也不知道该咋弄了 > > 我也差不多。 来个联系方式(邮箱或者别的, 能比较快的联系上你的)? 讨论讨论? 我的邮箱[email protected]

> I saw that Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5] was used for the input data when the train was made.Face_verify.py is also used, > why is Normalize not used...