chr5tphr / zennit
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Why this job: works in the areas we cover, but does not say which job it does
What it does
Zennit (Zennit explains neural networks in torch) is a high-level framework in Python using Pytorch for explaining/exploring neural networks. Its design philosophy is intended to provide high customizability and integration as a standardized solution for applying rule-based attribution methods in research, with a strong focus on Layerwise Relevance Propagation (LRP). Zennit strictly requires models to use Pytorch's torch.nn.Module structure (including activation functions).
Get started
$ pip install zennit- Maintenance
- Active
- Last commit 6 months ago
- Stars
- 249
- +1 this week
- Licence
- LGPL-3.0
- Share-alike for changes
- Downloads for
- None listed
- No release files
- Latest version
- 1.0.0
- Released 15 months ago
- Built with
- Python
- 93% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 60% closed
- 23 still open
- Pull requests
- 170 merged
- 5 waiting
- Releases
- 17
- 0 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| shap / shap | 25,857 | 2 days ago | MIT | No downloads |
| mmschlk / shapiq | 794 | 7 days ago | MIT | No downloads |
| explainX / explainx | 455 | 4 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 93%
- Shell 7%
Topics
- lrp
- pytorch
- xai
- machine-learning
- attribution
- explainability
- python
- interpretability
- explainable-ai
- interpretable-ai
- feature-attribution
- interpretable-ml
Project record
- JobOther AI tools
- StatusListed
- Commits257
- Forks38
- Watching10
- Stars in 28 days+2
- CreatedNov 10, 2020
- First seen by usNov 7, 2026
- CheckedNov 8, 2026