transcranial/keras-js
Run Keras models in the browser, with GPU support using WebGL
This helps web developers integrate pre-trained machine learning models directly into web applications, allowing for real-time predictions and data processing within the user's browser. It takes Keras models, trained using frameworks like TensorFlow, and allows them to be used in a web environment. The primary user is a web developer building interactive, AI-powered user experiences.
4,968 stars. No commits in the last 6 months. Available on npm.
Use this if you are a web developer who needs to run Keras deep learning models directly within a user's web browser, leveraging their device's GPU for faster performance.
Not ideal if you need a currently maintained solution for deploying Keras models to the web, as this project is no longer active and recommends TensorFlow.js as an alternative.
Stars
4,968
Forks
494
Language
JavaScript
License
MIT
Category
Last pushed
Jun 15, 2022
Commits (30d)
0
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/transcranial/keras-js"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
OpenMined/syft.js
The official Syft worker for Web and Node, built in Javascript
nikhilk/node-tensorflow
Node.js + TensorFlow
ewfian/faiss-node
Node.js bindings for faiss
beenotung/tensorflow-helpers
Helper functions to use tensorflow in nodejs for transfer learning, image classification, and more
ml5js/ml5-library
Friendly machine learning for the web! 🤖