DCAGN (Deep Convolutional Generative Adversarial Network) is one of the early well-performing and stable approaches to generate images with adversarial training. Let's take a look back at the simple example in Chapter 1, Generative Adversarial Networks Fundamentals.
Here, even when we only train a GAN to manipulate 1D data, we have to use multiple techniques to ensure a stable training. A lot of things could go wrong in the training of GANs. For example, either a generator or a discriminator could overfit if one or the other does not converge. Sometimes, the generator only generates a handful of sample varieties. This is called mode collapse. The following is an example of mode collapse, where we want to train a GAN with some popular meme images in China called Baozou. We can see that our GAN is only capable of generating one or two...
