How it works...

Now, enough with the analogies, right? Let's restructure this into a game-theory-style problem-the minimax problem from the first GAN implementation. The following steps illustrate how we can create this type of problem:

Generator goal: Maximize the likelihood that the discriminator misclassifies its output as real
Discriminator goal: Optimize toward a goal of 0.5, where the discriminator can't distinguish between real and generated images

The Minimax Problem (sometimes called MinMax) is a theory that focuses on maximizing a function at the greatest loss (or vice versa). In the case of GANs, this is represented by the two models training in an adversarial way. The training step will focus on minimizing the error on the training loss for the generator while getting as close to 0.5 as possible on the discriminator (where the discriminator can't tell the difference between real and fake).

In the GAN framework, the generator will start to train alongside the discriminator; the discriminator needs to train for a few epochs prior to starting the adversarial training as the discriminator will need to be able to actually classify images. There's one final piece to this structure, called the loss function. The loss function provides the stopping criteria for the Generator and Discriminator training processes. Given all of these pieces, how do we structure these pieces into something we can train? Check out the following diagram:

A high-level description of the flow of the Generative Adversarial Network, showing the basic functions in block format

With this architecture, it's time to break each piece into its component technology: generator, discriminator, and loss function. There will also be a section on training and inference to briefly cover how to train the model and get data out once it is trained.

Table of Contents for How it works...

Create new playlist

Sign In

Sign Up

Table of Contents for
How it works...