lyttonhao / Neural-Style-MMD

MXNet Code For Demystifying Neural Style Transfer (IJCAI 2017)
83 stars 22 forks source link

confusion in Linear Kernel Loss functions #2

Open allugrasm opened 7 years ago

allugrasm commented 7 years ago

I'm trying to understand the code but unable to understand your loss calculation function can you please explain what are you doing because it doesn't seem you are doing anything in linear kernel you have commented it out in mmd_loss.py

lyttonhao commented 7 years ago

Since the forward step is not necessary for optimizing, we comment the codes to save the time. We will refine the codes recently. Thanks!