Dogs vs Cats is too easy

The Dogs vs Cats problem has become a sort of hello world for deep learning folks. Many courses and blog posts that are aimed at beginners use it as the fundamental building block for an introduction into the exciting world of deep learning. Fastai has not been any different with past versions of the course focusing on building a Dogs vs Cats classifier in the first lesson. So the Dogs vs Cats problem is no longer challenging which means there is no opportunity to try out new ideas. A more challenging problem that Jeremy suggests is fine-grain classification.