understandable-machine-intelligence-lab/Quantus
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
When you're building or using AI models, it's crucial to understand why they make certain decisions. This toolkit helps you quantitatively evaluate how well those 'explanation methods' actually work. You input a neural network model and its explanations, and it outputs a score that tells you how reliable or faithful those explanations are. This is for AI practitioners, researchers, and anyone who needs to ensure their AI models are transparent and trustworthy.
647 stars. Used by 1 other package. Available on PyPI.
Use this if you need to objectively compare different AI explanation techniques or rigorously assess the quality and trustworthiness of an AI model's reasoning.
Not ideal if you are looking for a tool to generate initial AI explanations rather than evaluate existing ones.
Stars
647
Forks
88
Language
Jupyter Notebook
License
—
Last pushed
Mar 09, 2026
Commits (30d)
0
Dependencies
9
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/understandable-machine-intelligence-lab/Quantus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...