huoyijie

`1.Does this mean to train the network in a coarse-to-fine process, which initals the network from 256x256 and then finetunes it on larger sizes?` Yes `2.Does this accelerate the converge...

@gankzhang 你好，旷视(face++)公司没有有联系过我，所以没有授权过商业应用，谢谢！