distance-explainer

XAI method to explain distances in embedded spaces

https://github.com/dianna-ai/distance_explainer

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 3 DOI reference(s) in README
  • Academic publication links
    Links to: zenodo.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

XAI method to explain distances in embedded spaces

Basic Info
  • Host: GitHub
  • Owner: dianna-ai
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 275 KB
Statistics
  • Stars: 2
  • Watchers: 3
  • Forks: 0
  • Open Issues: 2
  • Releases: 4
Created almost 3 years ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

DOI workflow pypi badge

distance_explainer

XAI method to explain distances in embedded spaces.

overview schema

Installation

There are 2 ways to install distanceexplainer. To install distanceexplainer from PyPI (recommended) run:

console pip install distance_explainer

To instead install distance_explainer from the GitHub repository, run:

console git clone git@github.com:dianna-ai/distance_explainer.git cd distance_explainer python3 -m pip install .

How to use

See our tutorial how to use this package. In short: ```python image1 = np.random.random((100, 100, 3)) image2 = np.random.random((100, 100, 3))

image2embedded = model(image2) explainer = DistanceExplainer(axislabels={2: 'channels'}) attributionmap = explainer.explainimagedistance(model, image1, image2embedded) ```

Contributing

If you want to contribute to the development of distance_explainer, have a look at the contribution guidelines.

Credits

This package was created with Cookiecutter and the NLeSC/python-template.

Owner

  • Name: Deep Insight And Neural Network Analysis (DIANNA)​
  • Login: dianna-ai
  • Kind: organization
  • Location: Amsterdam

Netherlands eScience Center and SURF project to build software for post-hoc explainability of deep neural networks for scientists​

Citation (CITATION.cff)

# YAML 1.2
---
cff-version: "1.2.0"
title: "distance_explainer"
authors:
  -
    family-names: Meijer
    given-names: Christiaan
    orcid: "https://orcid.org/0000-0002-5529-5761"
  -
    family-names: Bos
    given-names: Patrick
    orcid: "https://orcid.org/0000-0002-6033-960X"

date-released: 2023-10-19
doi: 10.5281/zenodo.10018768.
version: "0.4.0"
repository-code: "git@github.com:dianna-ai/distance_explainer"
keywords:
  - XAI
  - embedded spaces
message: "If you use this software, please cite it using these metadata."
license: Apache-2.0

GitHub Events

Total
  • Issues event: 9
  • Watch event: 1
  • Delete event: 2
  • Issue comment event: 6
  • Push event: 8
  • Pull request event: 10
  • Create event: 3
Last Year
  • Issues event: 9
  • Watch event: 1
  • Delete event: 2
  • Issue comment event: 6
  • Push event: 8
  • Pull request event: 10
  • Create event: 3

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 30 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 1
  • Total maintainers: 2
pypi.org: distance-explainer

XAI method to explain distances in embedded spaces

  • Versions: 1
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 30 Last month
Rankings
Dependent packages count: 10.1%
Average: 33.4%
Dependent repos count: 56.8%
Maintainers (2)
Last synced: 10 months ago