Welcome to Torch Uncertainty¶
Welcome to the documentation of TorchUncertainty.
This website contains the documentation for installing and contributing to TorchUncertainty, details on the API, and a comprehensive list of the references of the models and metrics implemented.
Installation¶
Make sure you have Python 3.10 or later installed, as well as Pytorch (cpu or gpu).
pip install torch-uncertainty
To install TorchUncertainty with contribution in mind, check the contribution page.
Official Implementations¶
TorchUncertainty also houses multiple official implementations of papers from major conferences & journals.
A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors
Authors: Olivier Laurent, Emanuel Aldea, and Gianni Franchi
Paper: ICLR 2024.
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification
Authors: Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, and Isabelle Bloch
Paper: IEEE TPAMI.
Packed-Ensembles for Efficient Uncertainty Estimation
Authors: Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, and Gianni Franchi
Paper: ICLR 2023.
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks
Authors: Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Angel Tena, Rémi Kazmierczak, Séverine Dubuisson, Emanuel Aldea, David Filliat
Paper: BMVC 2022.