Hoff97/tensorjs

Deep learning for the Web

29
/ 100
Experimental

This is a JavaScript/TypeScript library designed for web developers to integrate machine learning and deep learning directly into web browsers. It allows you to perform numerical computations with multi-dimensional arrays (tensors) and run pre-trained ONNX models efficiently within a web application. Developers can input data like images or videos and get back processed tensors or model predictions, enabling interactive AI experiences.

No commits in the last 6 months.

Use this if you are a web developer building interactive web applications that need to perform complex numerical computations or run deep learning models directly in the user's browser, especially leveraging GPU for speed.

Not ideal if you need a server-side solution for deep learning inference or training, or if you require full support for all ONNX operators and maximum numerical precision not always available with WebGL.

web-development machine-learning-in-browser deep-learning-inference front-end-ai numerical-computation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

38

Forks

2

Language

TypeScript

License

MIT

Last pushed

Apr 07, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Hoff97/tensorjs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.