westnight

@ruinmessi Have you figure it out? Looking forward

> , but when I uesd the whole train data , which is the same as anno_train.txt, the result of RNET can not 我碰到另一个问题，整个模型对小人脸的检测效果还可以，但是对大人脸非常差，你碰到了吗

> If you are using one GPU, then you should able to get around 0.90 in easy set in about 84000 iterations. If you are using 4 GPU, 21000 is...

I din‘t use eval.py, maybe something is wrong with my code. I have another question. We often have large batchsize in recognition task like imagenet, can you tell me if...

> Please check whether model save directory exists or not. > I am traveling right now, I will upload as soon as I get back. But you should able to...

ok, I know, thank you. So when test on wider face, what we care about is recall. When I test mtcnn, the threshold can be set very low too, like...

我用全连接层匹配的方式训练了一把，在私人数据集上的结果是82%，arcface是84%。

> > 我用全连接层匹配的方式训练了一把，在私人数据集上的结果是82%，arcface是84%。 > > 请问你的setting是啥呀，BatchSize 是多少呢？ m,s和论文一致，bs200