pietrobarbiero/pytorch_explain
PyTorch Explain: Interpretable Deep Learning in Python.
Building deep learning models often means sacrificing understanding for performance. This library provides tools to create deep learning models that not only perform well but also explain their decisions using human-understandable 'concepts.' It takes raw data and outputs a model that makes predictions along with logical explanations for those predictions. This is for machine learning practitioners, researchers, and data scientists who need to build trustworthy and transparent AI systems.
172 stars. No commits in the last 6 months.
Use this if you need to develop deep learning models where understanding why a prediction was made is as important as the prediction itself, moving beyond the accuracy-interpretability trade-off.
Not ideal if your primary concern is raw predictive accuracy without any need for human-readable explanations or if you are not working with PyTorch deep learning models.
Stars
172
Forks
17
Language
Jupyter Notebook
License
Apache-2.0
Last pushed
May 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pietrobarbiero/pytorch_explain"
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...