znxlwm / pytorch-CartoonGAN

Pytorch implementation of CartoonGAN (CVPR 2018)
MIT License
386 stars 74 forks source link

Why do we need the last activation layer? #5

Open Dave1991 opened 5 years ago

Dave1991 commented 5 years ago

In the networks.py, I saw the last layer for generator is tanh, and the last layer for discriminator is sigmoid. However, in the network architecture proposed on the paper, the generator and the discriminator doesn't seem to need the last activation layer. Why do we add them?