Torch Uncertainty NeurIPS Experiments

Library of model configurations to reproduce the benchmark from TorchUncertainty's paper.

This repository contains the original configuration files for time-series classification (UCR-UEA) and semantic segmentation (MUAD).

These model configurations will work until at least torch-uncertainty==0.10.1.

Usage examples

Classification

UCR-UEA Example:

• Training an Inception Time model:

python main.py fit --config configs/beef/inception-time/standard.yaml

Citation

If you find this repository useful for your research, please consider citing

@inproceedings{lafage2025torch,
  title={Torch-Uncertainty: Deep Learning Uncertainty Quantification},
  author={Lafage, Adrien and Laurent, Olivier and Gabetni, Firas and Franchi, Gianni},
  booktitle={NeurIPS D&B}
  year={2025}
}