How deeply does Web Components in Action cover TensorFlow.js?

Explains browser inference and integration, but leaves model-training details largely outside the treatment.

TensorFlow.js

As explained in Web Components in Action

TensorFlow.js is a JavaScript library for developing and executing machine-learning models in web browsers and other JavaScript environments.

TensorFlow.js lets a trained machine-learning model run in a browser. A hand-recognition model trained with Google’s TensorFlow framework in Python can be used through JavaScript, while the training process itself remains outside the browser. section 15.4

A browser hand-tracking integration typically combines these pieces:

Render tracking details to a canvas while using a Web Component to hide the library and video-processing complexity. section 15.4

Hand-tracking Web Component

Extend a video component, load the hand-tracking model in the constructor, and call detect on the component’s video element. A demo page supplies the non-module Handtrack.js dependency, enables camera and canvas display, and listens for hand-location events. The same component can drive a Web Harp interface.

How Web Components in Action covers it

liveBook manning.com

Read Web Components in Action on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Deep Learning with Python, Third EditionA JavaScript TensorFlow ecosystem library for running models in browsers or other JavaScript environments.
liveBook manning.com

Deep Learning with R, Third EditionTensorFlow.js is a JavaScript library for running and developing machine-learning models in browsers and JavaScript environments.

Compare how 3 books explain TensorFlow.js →

Related concepts

JavaScriptuses · JavaScript is a high-level, dynamically typed, multi-paradigm programming language standardized as ECMAScript and used for web and general-purpose programming.
Kerasimplements · Keras is an open-source, high-level deep-learning API for building, training, evaluating, and deploying neural-network models.
data modelused by · A data model is a structured representation of data that defines its entities, attributes, relationships, and applicable constraints.

This explainer was generated by Manning's knowledge graph from the text of Web Components in Action. The section links point to the parts of the book it draws on.