Given an image of a dog, your algorithm identifies an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed. It can be used within a web or mobile app to process real-world, user-supplied images
Along with exploring state-of-the-art CNN models for classification and localization, important design decisions were made about the user experience for the app. Each model has its strengths and weaknesses, and engineering a real-world application often involves solving many problems without a perfect answer. An imperfect solution will nonetheless create a fun user experience!