Let's get started! We will first train a model for image classification that we can use later in the chapter to decide whether a photo contains a hot dog.
Training a model
To train a model for image classification, we need to collect photos of hot dogs and photos that aren't of hot dogs. Because most items in the world are not hot dogs, we need more photos that don't contain hot dogs. It's better if the photos of hot dogs cover a lot of different hot-dog scenarios—with bread, with ketchup, or with mustard. This is so the model will be able to recognize hot dogs in different situations. When we are collecting photos that aren't of hot dogs, we also need to have a big variety of photos that are both of items that are similar to hot dogs and that are completely different from hot dogs.
The model that is in the solution on GitHub was trained with 240 photos, 60 of which were of hot dogs...