The goal of this package is to make it simple to add modern uncertainty quantification (UQ) techniques to existing PyTorch models to produce label predictions with calibrated probabilities and out-of-distribution indicators.
What's Changed
Overall: two minor bugfixes, testing coverage increased, improved type hinting, and more comprehensive CI tools and actions.
* Feature/beartype by nukularrr in https://github.com/mit-ll-responsible-ai/equine/pull/21
* Stevenjson/patch 1 by nukularrr in https://github.com/mit-ll-responsible-ai/equine/pull/22
* Distance update by RoundOffError in https://github.com/mit-ll-responsible-ai/equine/pull/28
* Auto-updated dependencies with dependabot
**Full Changelog**: https://github.com/mit-ll-responsible-ai/equine/compare/v0.1.1...v0.1.2