I'm a little confused, I applied an existing code to the cgan and then plotted a plot diagram for the loss. It showed me three vector values of loss for the generator while the discriminant took only one loss vector. Why?
Asked
Active
Viewed 51 times
0
-
Please provide enough code so others can better understand or reproduce the problem. – lepsch Aug 27 '22 at 22:25
-
Additional to the adversarial loss, generators often incooperate further loss terms into their training objectives. E.g. Loss_gen = Loss_adv + l1*loss_1 + l2*loss2, where l1 and l2 are scaling factors to give more or less importance to a single term. – Sascha Kirch Oct 03 '22 at 07:15