What is Keras?

Keras is an open-source library of neural network components written in Python. Keras is capable of running atop TensorFlow, Theano, PlaidML and others. The library was developed to be modular and user-friendly, however it initially began as part of a research project for the Open-ended Neuro-Electronic Intelligent Operating System or ONEIROS. The principal author of Keras is Francois Chollet, a Google engineer who also wrote XCeption, a deep neural network model. While Keras officially launched, it was not integrated into Google's TensorFlow core library until 2017. Additional support has also been added for Keras integration with Microsoft Cognitive Toolkit.

Comprised of a library of commonly used machine learning components including objectives, activation functions, and optimizers, Keras' open-source platform also offers support for recurrent and convolutional neural networks. Additionally, Keras offers mobile platform development for users intending to implement deep learning models on smartphones, both iOS and Android. As of 2018, the library has 22% usage across from its over 200,000 users.