© Charlie Gerard 2021
C. GerardPractical Machine Learning in JavaScripthttps://doi.org/10.1007/978-1-4842-6418-8_2

2. TensorFlow.js

Charlie Gerard1 
(1)
Les Clayes sous bois, France
 

TensorFlow.js is an open source JavaScript library for machine learning. It is developed by Google and is a companion library to TensorFlow, in Python.

This tool enables you to build machine learning applications that can run in the browser or in Node.js.

This way, users don’t need to install any software or driver. Simply opening a web page allows you to interact with a program.

2.1 Basics of TensorFlow.js

TensorFlow.js is powered by WebGL and provides a high-level layers API for defining models and low-level API (previously deeplearn.js) for linear algebra.
Figure 2-1

Visual ...

Get Practical Machine Learning in JavaScript: TensorFlow.js for Web Developers now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.