Metadata-Version: 2.1
Name: gradient-metrics
Version: 0.1.7
Summary: Neural Network Gradient Metrics with PyTorch
Home-page: https://github.com/RonMcKay/gradient_metrics
License: MIT
Author: Philipp Oberdiek
Author-email: git@oberdiek.net
Requires-Python: >=3.6.2,<4
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Dist: numpy
Requires-Dist: torch (>=1.4.0)
Project-URL: Repository, https://github.com/RonMcKay/gradient_metrics
Description-Content-Type: text/markdown

<div align="center">

[![PyPI](https://img.shields.io/pypi/v/gradient-metrics)](https://pypi.org/project/gradient-metrics/) ![GitHub Workflow Status (branch)](https://img.shields.io/github/workflow/status/ronmckay/gradient_metrics/Publish%20to%20PyPI/main) [![](https://img.shields.io/badge/code%20style-black-black)](https://github.com/psf/black) [![PyPI - License](https://img.shields.io/pypi/l/gradient-metrics)](LICENSE) ![PyPI - Downloads](https://img.shields.io/pypi/dm/gradient-metrics)

</div>

# Installation

```python
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](https://arxiv.org/abs/1805.08440)".

Documentation and examples can be found on [GitHub pages](https://ronmckay.github.io/gradient_metrics/).

# 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 },  
}
