if dont't resample the data again, what will happen

AlexiaJM / RelativisticGAN

Code for replication of the paper "The relativistic discriminator: a key element missing from standard GAN"

719 stars 103 forks source link

if dont't resample the data again, what will happen #18

Closed 2018hello closed 5 years ago

2018hello commented 5 years ago

hi I see in Relativistic average Standard GAN code. It said "You may want to resample again from real and fake data" And so,if I dont't resample the data again, what will happen?

AlexiaJM commented 5 years ago

Nothing, it's just add some stochasticity/randomness. It doesn't change results much, so it might just be personal preferences.

You train D using real sample A and and fake sample B. You train G using real sample A and and fake sample B. vs You train D using real sample A and and fake sample B. You train G using real sample C and and fake sample D.