The imgaug library is commonly used in deep learning research and this figure demonstrates a subset of available augmentations in this free-to-use library:

Data augmentation is a cornerstone of deep learning data analysis. Each project needs to understand how data augmentation can improve their project. Why would you choose to include data augmentation in your project? In images, it's easy to understand. By augmenting your data—think flipping, noise, and so on—you are essentially forcing the algorithm to understand the content of the image without memorizing or keying in on singular features. With the advent of deep learners, it's now possible for discriminative modeling techniques to memorize entire datasets or hyper focus on singular features that make the learning component easy (think fast convergence during the training step). It's imperative that we use techniques such as data augmentation to force generalization during training. For a generative modeling architecture such as GANs, we will need to be fairly selective about which augmentations we use during training. This will be addressed in certain recipes throughout this book.