qingzhouzhen

what your problem? @twmht , my problem is I pretrain pvanet on ImageNet2012 got 66%, not 70%, I want to transfer pvanet to MXNet.

--lr-factor=0.36 --lr-step-epoch=30,60,80,100,120,140 --num-epochs=160 by the way, what is your framework? Caffe , TensorFlow, or Mxnet

I do not no what is plateau, MXNET does not have this , at least I do not know.

did you trid out the train detail on ImageNet2012? @chituma110 , I did train pvanet on ImageNet2012, but got 66.2%, not 70%

Why almost no research on class agostic detection? I guess: 1. no dataset for class agostic detection, (As I know, ImageNet has a subtask about class agostic detection, but seems...