Computer vision is the science of understanding or manipulating images and videos. Computer vision has a lot of applications, including autonomous driving, industrial inspection, and augmented reality. The use of deep learning for computer vision can be categorized into multiple categories: classification, detection, segmentation, and generation, both in images and videos. In this book, you will learn how to train deep learning models for computer vision applications and deploy them on multiple platforms. We will use TensorFlow, a popular python library for deep learning throughout this book for the examples. In this chapter, we will cover the following topics:
- The basics and vocabulary of deep learning
- How deep learning meets computer vision?
- Setting up the development environment that will be used for the examples covered in this book
- Getting a feel for TensorFlow, along with its powerful tools, such as TensorBoard and TensorFlow Serving
