search

krumo / Domain-Adaptive-Faster-RCNN-PyTorch

Domain Adaptive Faster R-CNN in PyTorch
MIT License
304 stars 68 forks source link

rpn loss #21

Closed Feobi1999 closed 3 years ago

Feobi1999 commented 3 years ago

When calculating the loss of the rpn part, how do you deal with the label of the target domain? I found you treat source and target domain data equally？I only notice you process the target domain label when calculate the loss of roi head. Looking forward to your reply

krumo commented 3 years ago

Thanks for your interest! When computing rpn loss, the labels of target domain are ignored at here.