Fei-Fei Huang comments

Results 4 comments of


                                            Fei-Fei Huang

I also met this issue with pytorch=0.4.1 And I solved this problem by updating pytorch 0.4.1 to 1.2 hope this will help you.

pix2pix and pix2pixHD need pairwise train dataset

CycleGAN used least-squares loss. You can check the paper: Least Squares Generative Adversarial Networks - ICCV 2017

Hi, Amazing work, can you please share with me your dataset? my email: [email protected] Thank you