bminixhofer/tractjs
Run ONNX and TensorFlow inference in the browser.
This project helps web developers integrate pre-trained machine learning models directly into web applications, allowing for predictions to happen right in the user's browser without sending data to a server. You provide an ONNX or TensorFlow model, and it outputs the prediction results. It's used by front-end developers building interactive web experiences powered by AI.
No commits in the last 6 months.
Use this if you are a web developer who needs to run machine learning models (like image classifiers or natural language processors) directly in a user's web browser, especially with recurrent neural networks (LSTMs) or decision tree classifiers.
Not ideal if your web application is extremely size-sensitive, as the library itself has a relatively large file size, or if you require GPU acceleration via WebGL/WebNN.
Stars
75
Forks
7
Language
Rust
License
—
Category
Last pushed
Jan 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bminixhofer/tractjs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tensorflow/tfjs
A WebGL accelerated JavaScript library for training and deploying ML models.
nnstreamer/api
Machine Learning API (Origin: C++: SNAP, C/C#: Tizen API, Java: Samsung-Research ML API). For...
microsoft/DMTK
Microsoft Distributed Machine Learning Toolkit
R-js/blasjs
Pure Javascript manually written :ok_hand: implementation of BLAS, Many numerical software...
tensorflow/tfjs-core
WebGL-accelerated ML // linear algebra // automatic differentiation for JavaScript.