In this chapter, we will learn about TensorFlow, which is one of the most popularly used deep learning libraries. Throughout this book, we will be using TensorFlow to build deep learning models from scratch. So, in this chapter, we will get the hang of TensorFlow and its functionalities. We will also learn about TensorBoard, which is a visualization tool provided by TensorFlow used for visualizing models. Moving on, we will learn how to build our first neural network, using TensorFlow to perform handwritten digit classification. Following that, we will learn about TensorFlow 2.0, which is the latest version of TensorFlow. We will learn how TensorFlow 2.0 differs from its previous versions and how it uses Keras as its high-level API.

In this chapter, we will cover the following topics:

• TensorFlow
• Computational graphs and sessions
• Variables, constants, and placeholders
• TensorBoard
• Handwritten digit classification in TensorFlow
• Math operations in TensorFlow
• TensorFlow 2.0 and Keras