pyc-team/pytorch_concepts

PyC (Pytorch Concepts) is a PyTorch-based library for training concept-based interpretable deep learning models.

60
/ 100
Established

This library helps machine learning engineers and researchers build deep learning models that are understandable and explainable. It takes your raw data and model specifications as input, then outputs a trained deep learning model where you can see how specific 'concepts' influence its predictions, rather than just getting a black-box answer. It's for those who need to justify or interpret their AI's decision-making process.

Available on PyPI.

Use this if you need to understand *why* your deep learning model makes certain predictions, especially in fields where model transparency is crucial.

Not ideal if you solely need to maximize predictive accuracy without any requirement for model interpretability or causal understanding.

explainable-AI model-interpretability AI-transparency causal-inference machine-learning-engineering
Maintenance 10 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

31

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pyc-team/pytorch_concepts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.