Why do you leave out batch norm on the first iteration of creating the discriminator for GAN.py?
pyoungkangkim opened this issue · comments
It kind of struck my curiosity on why you left out Batchnorm on iteration 0.
https://github.com/davidADSP/GDL_code/blob/master/models/GAN.py#L105
Hi @MLSlayer / anyothers , could you find any information on why the BN is omitted in 0'th iteration? Also, this same logic appears in the below forked code
https://github.com/MLSlayer/Generative-Deep-Learning-Code-in-Pytorch/blob/49bd308a344f7c0710fbbb4004b726b372104959/models/GAN.py#L46