mitvis/saliency-cards
Saliency Cards are transparency documentation for saliency methods. Learn about new saliency methods or document your own!
This project helps machine learning researchers and practitioners understand and compare different 'saliency methods' used to explain AI model decisions. You input information about a specific saliency method, like how it handles hyperparameters or changes to input, and it helps you document or evaluate its characteristics. This is for anyone who uses or develops AI explanation techniques.
No commits in the last 6 months.
Use this if you need to analyze, document, or compare the behavior and attributes of various saliency methods for explaining AI models.
Not ideal if you are looking for a tool to generate saliency maps or explanations directly from your AI model, as this focuses on documentation and comparison of methods.
Stars
19
Forks
1
Language
Jupyter Notebook
License
—
Last pushed
Jun 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mitvis/saliency-cards"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...