TensorFlow is a full-blown, ML research and production tool. It can be very complex—but it doesn’t have to be. Like an Excel spreadsheet, TensorFlow can be used simply or more expertlyTensorFlow has a rich set of tools. For example, the activation functions for neural networks can do all the hard work of statistics.
Example -
• Run on both CPUs and GPUs
• Perform regression, classification, neural networks, etc.

Keras is a neural network library built on top of TensorFlow to make ML modeling straightforward. It simplifies some of the coding steps, like offering all-in-one models, Kera's can also use the same code to run on a CPU or a GPU.
Example -
• Microsoft Cognitive Toolkit (CNTK)
• R Programming
• Theano
• PlaidML