In this chapter's example, I will be working with Kaggle's Dogs versus Cats dataset. This dataset consists of 25,000 images of dogs and cats. It's perfectly balanced between classes at 12,500 each. The dataset can be downloaded from https://www.kaggle.com/c/dogs-vs-cats/data.

This is a binary classification problem. Each photograph contains either a dog or a cat, but not both.

This dataset was assembled in 2007 by Jeremy Elson et. al of Microsoft Research, and it's currently hosted at www.kaggle.com. It's absolutely free to download and use for academic use, but it does require a Kaggle account and acceptance of their end user license. Just the same, it's a fantastic dataset so I'm including instructions for using it here.