This final section addresses several contemporary challenges in our domain and provides essential techniques for those who want to apply computer vision to novel use cases. First, TensorFlow tools that are designed to process large amounts of data in an efficient manner are presented. Tackling the opposite scenario, where data is too scarce, you will also be introduced to domain adaptation, as well as image generation with computer graphics, GANs, and VAEs. To learn how to extract information from videos, a chapter is dedicated to recurrent neural networks, their theory, and some illustrated applications. Finally, the book ends with a discussion about the challenges related to on-device computer vision, teaching you how to deploy your solutions on mobile phones and in web browsers.
The following chapters will be...
