slimgroup/InvertibleNetworks.jl

A Julia framework for invertible neural networks

45
/ 100
Emerging

This tool helps researchers and practitioners in scientific computing and machine learning build neural networks that are memory-efficient and interpretable. It takes raw data or intermediate network activations and transforms them, providing both the forward result and the ability to perfectly reverse the process. Anyone working on tasks like uncertainty quantification, generative models, or image reconstruction with large datasets would find this useful.

169 stars. No commits in the last 6 months.

Use this if you need to build neural networks that are memory-efficient, allow for exact reconstruction of input data, and provide robust uncertainty estimates in scientific applications.

Not ideal if your primary goal is standard deep learning classification or regression without the specific need for invertibility or detailed uncertainty quantification.

scientific-machine-learning uncertainty-quantification generative-modeling image-reconstruction high-performance-computing
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

169

Forks

24

Language

Julia

License

MIT

Last pushed

Oct 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/slimgroup/InvertibleNetworks.jl"

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