Ning Lu

det 正常

识别还是有问题，现在没空弄了。

@northeastsquare @MiZhangWhuer hi, two guys, I understand your concern. I am still verifying the recognition branch's correctness, If I have any news, I will tell you. I have same problem...

@junwenZhang 参考我的 repo做法 https://github.com/jiangxiluning/facenet_mtcnn_to_mobile

1 个pb 一个 模型， 3 个pb 合 1个的话，你需要再 写入二进制的时候 自己做 binary 级别的分隔符，比如定义 magic number 来作为分隔符

你的根本需求是需要一个模型还是三个模型

@vcvycy 对，你这个不错

@Smith42 hi， I trained it with cifar-10. The batch size is 16. The image size is 128. The loss is about 0.05. But the generated images are seemed as being...

@cajoek for me, it is L1.

@Xujianzhong 方便贴下代码链接么，我没有指定h为1。