bmucsanyi/untangle

Large-scale uncertainty benchmark in deep learning.

37
/ 100
Emerging

This tool helps deep learning researchers and practitioners evaluate and compare different methods for quantifying uncertainty in their AI models, particularly for image classification tasks. It takes various uncertainty quantification techniques and image datasets (like CIFAR-10, ImageNet) as input and outputs performance metrics and visualizations for how well these methods estimate model confidence and error. The primary user is a deep learning researcher or ML engineer focused on robust AI systems.

No commits in the last 6 months.

Use this if you are a deep learning researcher or practitioner needing to benchmark and compare various uncertainty quantification methods for image classification models under different conditions, including noisy or out-of-distribution data.

Not ideal if you are looking for a plug-and-play solution for production-ready uncertainty estimation without needing to rigorously benchmark and disentangle different uncertainty types.

deep-learning-research uncertainty-quantification image-classification model-robustness AI-benchmarking
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

64

Forks

7

Language

Python

License

Apache-2.0

Last pushed

May 10, 2025

Commits (30d)

0

Get this data via API

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

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