gradient_metrics 0.2.0

Neural Network Gradient Metrics with PyTorch

Installation

pip install gradient-metrics

This package implements utilities for computing gradient metrics for measuring uncertainties in neural networks based on the paper "Classification Uncertainty of Deep Neural Networks Based on Gradient Information".

Documentation and examples can be found on GitHub pages.

Citing

@inproceedings{OberdiekRG18,
author = {Philipp Oberdiek and
Matthias Rottmann and
Hanno Gottschalk},
editor = {Luca Pancioni and
Friedhelm Schwenker and
Edmondo Trentin},
title = {Classification Uncertainty of Deep Neural Networks Based on Gradient
Information},
booktitle = {Artificial Neural Networks in Pattern Recognition - 8th {IAPR} {TC3}
Workshop, {ANNPR} 2018, Siena, Italy, September 19-21, 2018, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {11081},
pages = {113--125},
publisher = {Springer},
year = {2018},
url = { https://doi.org/10.1007/978-3-319-99978-4_9 },
doi = { 10.1007/978-3-319-99978-4_9 },
}