junyanz / pytorch-CycleGAN-and-pix2pix

Image-to-Image Translation in PyTorch
Other
23.09k stars 6.32k forks source link

Question on semantic loss of CycleGANSemanticModel #1508

Closed yklInverted closed 2 years ago

yklInverted commented 2 years ago

Hi, I got a bit confused about the implementation of the semantic loss in the CycleGANSemanticModel. In your CyCADA paper, the semantic consistency loss is computed using a pretrained model fs. However, in this code I found that the semantic loss is directly computed using the target model ft. I just wonder why the implementation differs and how will this influence the result.