stavrostheocharis/easy_explain
An XAI library that helps to explain AI models in a really quick & easy way
This tool helps AI researchers and developers understand why their image-based AI models make specific predictions. You feed in an image and your trained AI model, and it outputs visual explanations like heatmaps showing which parts of the image were most important to the model's decision. It's designed for anyone working with computer vision models who needs to interpret their behavior.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer or researcher developing image classification or object detection models and need to explain their internal decision-making process in a straightforward way.
Not ideal if you need to explain models that don't process images, such as those working with text, tabular data, or time series.
Stars
17
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 08, 2024
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/stavrostheocharis/easy_explain"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shap/shap
A game theoretic approach to explain the output of any machine learning model.
mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
iancovert/sage
For calculating global feature importance using Shapley values.
predict-idlab/powershap
A power-full Shapley feature selection method.
aerdem4/lofo-importance
Leave One Feature Out Importance