search

tiancity-NJU / da-faster-rcnn-PyTorch

An unofficial implementation of 'Domain Adaptive Faster R-CNN for Object Detection in the Wild ’
Other
136 stars 37 forks source link

why set the alpha to 0.1？ #10

Open 1453042287 opened 5 years ago

1453042287 commented 5 years ago

https://github.com/tiancity-NJU/da-faster-rcnn-PyTorch/blob/47cd8a80f4811a504d4cb57d2b21401ccd2b1151/lib/model/da_faster_rcnn/DA.py#L29 with the alpha=0.1 and arg.lamda=0.1, the total scale seem to be 0.01?

stormchasingg commented 5 years ago

lambda=0.1 for loss lambda*alpha=0.01 for back propagation