TensorFlow and Keras Fundamentals
Mehdi Ghayoumi · 2021
Google created TensorFlow in Google Brain. TensorFlow is a numerical computations framework for machine learning algorithms, especially deep neural networks. The computation in TensorFlow is in a dataflow graph format, and in each graph, some operations like addition, represented by nodes and edges, define the data. Tensor board is a toolkit for TensorFlow that helps us to follow the TensorFlow process visually. Keras is one of the easy platforms to use python libraries and is on top of some machine learning platforms like TensorFlow to create deep learning models. This chapter reviews some fundamentals and main concepts of the Keras and explain them with some examples. After importing the libraries, we should train the model and test it. The chapter presents some modules in Keras that we can use. The Keras API has three main parts: model, layer, and modules.