Keras is an open source neural network library written in Python. This book will help you to experiment with deep neural networks as simply as possible. Its principal author and maintainer is François Chollet, a Google engineer. In 2017, Google's TensorFlow team decided to support Keras in TensorFlow's main library. Keras contains several implementations of commonly used neural network blocks, such as levels, objectives, activation functions, optimizers, and a set of tools to facilitate work with image and text data. In this chapter, an overview of the Keras environment will be addressed.
The following topics are covered:
- Introduction to Keras
- Keras backend options
- Model fitting in Keras
At the end of the chapter, the reader will learn how to work with the keras library, and how to install and configure Keras. We will also discover the basic concepts of the Keras architecture. We will learn how Keras uses TensorFlow as its tensor manipulation library. We will also understand the different type of Keras models, sequential and functional APIs, and learn how to implement Keras layers.