Does it generate the set of the same image classes in the same order on each iteration? If yes, what's the usufullness of that ?


Does it generate the set of the same image classes in the same order on each iteration?

No, a basic generator in a GAN is typically fed a small random vector as input; e.g. a column of 100 gaussian samples, with mean 0, standard deviation 1. It then must use this random "embedding" in the feed forward network to produce output that is in the target distribution of real data that the discriminator is trying to assess it against.

So a GAN typically learns a mapping from an arbitrary relatively low dimensional space onto a higher-dimensional target space. DCGANs do this with image data.

The class of an image can be used as conditioning data, if it is fed as additional input to the the generator and discriminator. The sequence of image classes can be anything you like, and the GAN is not required to work in a particular sequence (unless perhaps you are working with a RNN-based GAN and are trying to learn to produce sequences).

What exactly does generator produce in DCGANs?

It produces an output image depending on the input. The output is drawn from a distribution based on the training data, that the discriminator would struggle to distinguish from real data. If fed a random input vector, generated in same way as training stages, then the idealised output should appear to have been drawn equally randomly from the imagined population of all possible training data.

  • $\begingroup$ I'm referring this article medium.freecodecamp.org/…. They do not use any class information as generator/discriminator loss. So I was wondering how to achieve generator to know which class to generate? And does discriminator really need class information (it looks beyond its task)? $\endgroup$ Jul 8 '18 at 9:44
  • 1
    $\begingroup$ @VladimirLenin: A basic GAN doesn't know which class to generate, although the classes will probably get associated with different parts of the embedding vector space. You can add the class identity to both generator and discriminator if you want to do that. $\endgroup$ Jul 8 '18 at 9:50

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.