What exactly is the difference is between Keras and TensorFlow?
! Keras is actually integrated into TensorFlow. It’s a wrapper around the TensorFlow backend
Technically speaking, you could use Keras with a variety of potential backends.
But what exactly does that mean?
Basically, you are able to make any Keras call you need from within TensorFlow.
You get to enjoy the TensorFlow backend, while leveraging the simplicity of of Keras.
Here’s a great article on Medium that walks you through the process of creating a neural network with Keras.