djib2011/hide-and-seek
Repo for the paper: "Hide-and-Seek: A Template for Explainable AI", by Thanos Tagaris and Andreas Stafylopatis
This project helps data scientists and machine learning engineers understand why their image classification models make certain predictions. It takes an image and a trained neural network, then outputs both the classification and a 'mask' highlighting only the key parts of the image that influenced the decision. This allows practitioners to build trust in their AI systems by seeing what visual cues the model actually uses.
No commits in the last 6 months.
Use this if you need to explain the reasoning behind your neural network's image classification decisions to stakeholders or for debugging purposes.
Not ideal if your primary concern is solely achieving the highest possible predictive accuracy without needing any explanation of the model's choices.
Stars
7
Forks
1
Language
Jupyter Notebook
License
MIT
Last pushed
Jun 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/djib2011/hide-and-seek"
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...