ScottAlexanderCameron/Jynx

A neural network library written in jax

21
/ 100
Experimental

This library helps machine learning engineers or researchers quickly build and train neural networks using JAX. You provide your data and define your model's architecture using a collection of standard layers, then train it with the built-in `fit` function. The output is a trained neural network model ready for deployment or further experimentation.

No commits in the last 6 months.

Use this if you are a machine learning engineer who needs to quickly prototype and train neural networks in JAX, valuing transparency and control over hidden abstractions.

Not ideal if you prefer a high-level API with many pre-built, complex models and extensive automated features, or if you are not familiar with JAX or Optax.

neural-networks deep-learning model-training machine-learning-engineering ai-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

13

Forks

Language

Python

License

MIT

Last pushed

Feb 03, 2025

Commits (30d)

0

Get this data via API

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

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