A PyTorch Library for benchmarking and leveraging efficient predictive uncertainty quantification techniques.
Project description
TorchUncertainty is a package designed to help you leverage uncertainty quantification techniques and make your neural networks more reliable. It is based on PyTorch Lightning to handle multi-GPU training and inference and automatic logging through tensorboard.
:construction: TorchUncertainty is in early development :construction: - expect massive changes but do reach out to us and contribute if you are interested by the project!
This package provides a multi-level API, including:
- ready-to-train baselines on research datasets, such as ImageNet and CIFAR
- baselines available for training on your datasets
- pretrained weights for these baselines on ImageNet and CIFAR (work in progress 🚧).
- layers available for use in your networks
- post-processing methods such as temperature scaling
Installation
The package can be installed from PyPI:
pip install torch-uncertainty
To contribute, install the package from source following the instructions of the dedicated page in the documentation and activate the pre-commit hooks with pre-commit install
.
Getting Started and Documentation
Please find the documentation at torch-uncertainty.github.io.
A quickstart is available at torch-uncertainty.github.io/quickstart.
Implemented methods
Baselines
To date, the following baselines are implemented:
- Deep Ensembles
- BatchEnsemble
- Masksembles
- Packed-Ensembles (see blog post)
Post-processing methods
To date, the following post-processing methods are implemented:
- Temperature scaling
Tutorials
Awesome Uncertainty repositories
You may find a lot of information about modern uncertainty estimation techniques on the Awesome Uncertainty in Deep Learning.
Other References
This package also contains the official implementation of Packed-Ensembles.
If you find the corresponding models interesting, please consider citing our paper:
@inproceedings{laurent2023packed,
title={Packed-Ensembles for Efficient Uncertainty Estimation},
author={Laurent, Olivier and Lafage, Adrien and Tartaglione, Enzo and Daniel, Geoffrey and Martinez, Jean-Marc and Bursuc, Andrei and Franchi, Gianni},
booktitle={ICLR},
year={2023}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for torch_uncertainty-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d0b9962c71a4c08fb0ac95a476f9088cc6e9a950b7ba9368b37fbf0f33300a89 |
|
MD5 | 6deabe51e8e58520e7e2461e1279b04c |
|
BLAKE2b-256 | 7c36c944ee1b0b0451865fe6cdb49695b1d06c59bc33546bd0ba210b61b5f293 |