bmucsanyi/untangle
Large-scale uncertainty benchmark in deep learning.
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.
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.
Higher-rated alternatives
EmuKit/emukit
A Python-based toolbox of various methods in decision making, uncertainty quantification and...
google/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
nielstron/quantulum3
Library for unit extraction - fork of quantulum for python3
IBM/UQ360
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you...
aamini/evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!