Take some time to reinforce your learning by undertaking the following exercises:

1. What type of GAN would you use to transfer styles on an image?
2. What type of GAN would you use to isolate or extract the style?
3. Modify the number of critics used in the Wasserstein GAN example and see the effect it has on training.
4. Modify the first GAN, the DCGAN, to improve training performance using any technique you learned in this chapter. How did you increase training performance?
5. Modify the BatchNormalization momentum parameter and see what effect it has on training.
6. Modify a few of the samples by changing the activation from LeakyReLU to another advanced form of activation.
7. Modify the Wasserstein GAN example to use your own textures. There is a sample data loader available in the downloaded code sample for the chapter.
8. Download one of the other reference GANs from https://github.com/eriklindernoren/Keras-GAN and modify that to use your own dataset.
9. Alter the first music generation GAN to use a different corpus.  
10. Use your own MIDI files to train the second music generation GAN example.  
11. (BONUS) Which music GAN generated better music? Is it what you expected?

You certainly don't have to work through all these exercises, but give a few a try. Putting this knowledge to practice right away can substantially improve your understanding of the material. Practice does make perfect, after all.