As we mentioned earlier, we will be working on an image categorization problem with the constraint of having a small number of training samples per category. The dataset for our problem is available on Kaggle and is one of the most popular computer vision based datasets out there. The dataset we will be using comes from the Dogs vs. Cats challenge (https://www.kaggle.com/c/dogs-vs-cats/data), whereas our primary objective is to build a model that can successfully recognize and categorize images into either a cat or a dog. In terms of ML, this is a binary classification problem based on images.

To start, download the train.zip file from the dataset page and store it in your local system. Once downloaded, unzip it into a folder. This folder will contain 25,000 images of dogs and cats; that is, 12,500 images per category.