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

pip install torch-uncertainty

To install TorchUncertainty with contribution in mind, check the contribution page.

Packed-Ensembles

Finally, TorchUncertainty also includes the official PyTorch implementation for the following paper:

Packed-Ensembles for Efficient Uncertainty Estimation

• Authors: Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, and Gianni Franchi

• Paper: here.

Contents:

• Installation
  • From PyPI
  • From source
  • Options
• Quickstart
  • Training with TorchUncertainty’s Uncertainty-aware Routines
  • Using the Lightning CLI tool
  • Using the PyTorch-based models
  • Using the PyTorch-based layers
  • Other usage
• Tutorials
• CLI Guide
  • Introduction to the Lightning CLI
  • Configuration files
  • Experiment folder usage
• API Reference
  • Routines
  • Baselines
  • Layers
  • Models
  • Metrics
  • Losses
  • Post-Processing Methods
  • Datamodules
• Contributing
  • The scope of TorchUncertainty
  • Common guidelines
  • License
• References
  • Uncertainty Models
  • Data Augmentation Methods
  • Post-Processing Methods
  • Metrics
  • Datasets
  • Architectures
  • Layers

Indices and tables

• Index

• Module Index

• Search Page