yuhuayc/da-faster-rcnn

Is the consistency regularization exists in train.prototxt?

Closed this issue · 6 comments

It seems that the train.prototxt file does not contain the the consistency regularization in your paper.
Is there something I overlook? If not, could you supply a full file? Thanks a lot!

wjx2 commented

@FlyingQianMM
hi, do you get the full file?

No, exactly codes the author supplies now.

@FlyingQianMM
hi, do you run the codes with unlabeled target domain data set successfully?

@lly2111101
hi, do you run the codes with unlabeled target domain data set successfully so far?

Hi guys, please use the caffe2 implementation if you want to use consistency loss: https://github.com/krumo/Detectron-DA-Faster-RCNN

Yes!This is bothering me too