TreB1eN

@lianuo 如果想加速，还是要用c实现，或者Gpu

I don't think so, maybe you need to tune your lr if you change the batchsize

and about convergence, it will not converge at all after several epoches

that's not OK, the loss should start to decrease at very early stage

No，but welcome

also you can check on [this](https://github.com/TreB1eN/InsightFace_Pytorch/issues/20)

Yes, I noticed the difference a while ago, the drop_ratio is a mistake, the choice of se_model is just random. Please issue a PR if you can get better performace

no, you can have a try

I don't have clue about training Megaface, normally there are a lot of noises in the training set, how about try use emore dataset pretrained model here to test in...

I haven't