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.
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.