Importing CIFAR

Now that we've discussed the underlying theory of VAE algorithms, let's start building a practical example using a real-world dataset. As we discussed in the introduction, for the experiments in this chapter, we'll be working with the Canadian Institute for Advanced Research (CIFAR) 10 dataset.¹⁰ The images in this dataset are part of a larger 80 million "small image" dataset¹¹, most of which do not have class labels like CIFAR-10. For CIFAR-10, the labels were initially created by student volunteers¹², and the larger tiny images dataset allows researchers to submit labels for parts of the data.

Like the MNIST dataset, CIFAR-10 can be downloaded using the TensorFlow dataset's API:

import tensorflow.compat.v2 as tf
import tensorflow_datasets as tfds
cifar10_builder = tfds.builder("cifar10")
cifar10_builder.download_and_prepare()

This will download the dataset to disk and make it available for our experiments. To split...