Image To Image Translation On Zebra2Horse

Frechet Inception Distance

Number of params

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

			Paper Title
PoL (CycleGAN)	112.3	15.9M	Powers of layers for image-to-image translation
CycleGAN	110.5	28.2M	Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
U-GAT-IT	-	-	U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

0 of 3 row(s) selected.