Getting started with TensorFlow 2 and Keras

Before detailing the core concepts of TensorFlow, we will start with a brief introduction of the framework and a basic example.

Introducing TensorFlow

TensorFlow was originally developed at Google to allow researchers and developers to conduct machine learning research. It was originally defined as an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.

The main promise of TensorFlow is to simplify the deployment of machine learning solutions on various platforms—computer CPU, computer GPUs, mobile devices, and, more recently, in the browser. On top of that, TensorFlow offers many useful functions for creating machine learning models and running them at scale. In 2019, TensorFlow 2 was released with a focus on ease of use while maintaining good performance.

Note

An introduction to TensorFlow 1.0's concepts is available as an Appendix of this book.

The library was open-sourced in November 2015. Since...