WGAN_value_fct

The discriminator scores on real examples ($D(x)$)

real_scores

The discriminator scores on fake examples ($D(G(z))$)

fake_scores

Implements the Wasserstein GAN (WGAN) value function as a function to be called in gan_trainer.
Note that for this to work properly you also need to implement a weight clipper (or other procedure) to constrain the Discriminator weights.

An easy way to get started with Generative Adversarial Nets (GAN) in R. The GAN algorithm was initially
described by Goodfellow et al. 2014 <https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf>. A GAN can be used to learn the joint distribution of complex data by
comparison. A GAN consists of two neural networks a Generator and a Discriminator, where the two
neural networks play an adversarial minimax game.
Built-in GAN models make the training of GANs in R possible in one line and make it easy to
experiment with different design choices (e.g. different network architectures, value functions, optimizers).
The built-in GAN models work with tabular data (e.g. to produce synthetic data) and image data.
Methods to post-process the output of GAN models to enhance the quality of samples are available.

WGAN_value_fct: WGAN Value Function

Description

Usage

Arguments

Value