An Introduction to TensorFlow and Keras
In this section, both frameworks will be presented, thus providing you with a general overview of their architecture, the fundamental elements they are composed of, and listing some of their typical applications.
TensorFlow
TensorFlow is an open source numerical computation software library that leverages data flow computational graphs. Its architecture allows users to run it on a wide variety of hardware: from CPUs to Tensor Processing Units (TPUs), including GPUs as well as mobile and embedded platforms. The main difference between the three is the speed and the type of data they are able to perform computations with (multiplications and additions), which, of course, is of primary importance when aiming for maximum performance.
Note
We will be looking at various code implementation examples for TensorFlow in the Keras section of this chapter.
You can refer to the official documentation of TensorFlow for more information here...