What is Keras

Keras is an open source neural network library, which is written in Python.
Keras runs on top of other machine learning frameworks, such as TensorFlow, Microsoft's cognitive toolkit and Theano.
Keras is a high level API, which facilitates fast experimentation.
Keras was designed to facilitate fast experimentation with deep neural networks.
Keras is easy to use. It is modular and it's extensible.
Keras was designed to be an interface rather than a standalone machine learning framework.
Keras can be used in conjunction with CPUs and GPUs.
In 2017 Google's TensorFlow team decided to support Keras in Tensor Flow's core library.
TensorFlow Keras is TensorFlow's implementation of the Keras API specification.
TensorFlow Keras is a high-level API to build and train models that include first-class support for TensorFlow specific functionality.
TensorFlow Keras makes TensorFlow easier to use without sacrificing some of the flexibility and performance that is afforded by TensorFlow.

Note: There is always the option to use aspects of the TensorFlow library directly in the program without using the Keras API.

Knowledge Sharing