domain label prediction num_ouputs

Open lolongcovas opened this issue 9 years ago • 0 comments

Hi, Since there are 2 domain labels, the layer connected to SigmoidCrossEntropyLoss shouldnt be 2 instead of 1? please, see here: https://github.com/ddtm/caffe/blob/grl/examples/adaptation/protos/train_val.prototxt#L654

Nov 08 '16 20:11 lolongcovas