Malik

Results 2 issues of Malik

I saw that you are normalizing the embedding output [here](https://github.com/deepinsight/insightface/blob/master/recognition/arcface_mxnet/verification.py#L321). Do we need to normalize the embedding? Since, if I removed the normalization part, the performance drop significantly. But, how...

How do you save your model after the training is done?