jhoffman / cycada_release

Code to accompany ICML 2018 paper
BSD 2-Clause "Simplified" License
561 stars 126 forks source link

semantic consistency loss #47

Open yklInverted opened 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 the 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.