xhzcyc

I means that implement the yolo operator using python api of mxnet, not the c++. We can test the code directly, not to recompile the mxnet! Thanks!

When I trained it by following leonardoaraujosantos, I got this problem. WARNING:tensorflow:Error encountered when serializing LAYER_NAME_UIDS. Type is unsupported, or the types of the items don't match field type in...

I have read and implemented DSOD, but the result is not good! Have you tried it? @zhreshold

Did you solved your problem? Thanks @belleoct

My LFW training loss is about 0.01

How about your training result? @wuqianliang

What's the size of your lmdb file that generated from 20000 person's image?

Why are your test accuracy so low? I have trained 10000 people subset and get a good result!