luckycallor

@csqzs For both training and evaluation data, you can see the DataZoo of the official mxnet project: https://github.com/deepinsight/insightface/wiki/Dataset-Zoo

@xuweihuawei 训练代码里面每个batch都会打印出来训练损失和训练分类准确率，这里打印的训练准确率也是0吗？

@destiny311 arcface 的损失函数确实有一个更严格的分类平面，所以训练是的准确率会比较低，但不会一直是0，随着训练的进行，训练准确率会变大。

@luvwinnie I have the same problem. Do you have any idea to solve it?