caffe-fast-rcnn icon indicating copy to clipboard operation
caffe-fast-rcnn copied to clipboard

about smooth_l1_loss_layer

Open mjjdick opened this issue 6 years ago • 0 comments

Hi, I was confused about the smooth_l1_loss_layer.cu, that the diff_ in Forward_gpu has multiply the "inside" weights, why in Backward_gpu, multiply the "inside" weights again?

mjjdick avatar May 29 '18 09:05 mjjdick