search

roatienza / Deep-Learning-Experiments

Videos, notes and experiments to understand deep learning
MIT License
1.1k stars 760 forks source link

Freezing the Discriminator #9

Closed mohjaba closed 6 years ago

mohjaba commented 6 years ago

Hi, thank you very much for this wonderful example for implementing GAN using Keras. I have one question, based on what I understood from the theory that there are three stages GAN should be train with:

  1. training D for ground truth data as input with label 1 as output
  2. training D using G output as an input and label 0 as output
  3. same as (2) but with freezing D weights and label 1 as D output my question is: I didn't see any freezing step in your code. So, is that deferent way of implementation? or I miss something? Thanks again
roatienza commented 6 years ago

In some GAN training, they freeze the weights of the discriminator. Here, the discrimimator and generator are trained simultaneously.