PyTorch-GAN icon indicating copy to clipboard operation
PyTorch-GAN copied to clipboard

CycleGAN discriminator activation fucnction

Open KhrystynaFaryna opened this issue 4 years ago • 1 comments

I noticed that the discriminator does not have activation function in the output. The last layer is just a convolution. Why is that?

KhrystynaFaryna avatar Mar 08 '20 16:03 KhrystynaFaryna

CycleGAN used least-squares loss. You can check the paper: Least Squares Generative Adversarial Networks - ICCV 2017

IvanFei avatar Mar 30 '20 08:03 IvanFei