Open dupc2018 opened 1 year ago
rec_B works well, fake_B works poorly, identity 0.5, lambda_A, and lambda_B 10
Could you share more details?
Using a paired dataset, training the recurrent network was found to be very close rec_B to the real_B, and the fake_B was much different from both rec_B and real_B
rec_B works well, fake_B works poorly, identity 0.5, lambda_A, and lambda_B 10