serre-lab/Lens
LENS Project
This project helps machine learning practitioners understand why their image classification models make certain decisions. It takes an ImageNet-trained model and reveals the specific visual concepts it uses to classify images, showing what goes in and what comes out. It also identifies potential biases, helping those who deploy and maintain AI models gain trust and insights into their system's behavior.
No commits in the last 6 months.
Use this if you need to explain the reasoning behind an image classification model's predictions and uncover any unexpected biases it might have.
Not ideal if you are looking for explanations for models other than image classifiers or those not trained on ImageNet-like datasets.
Stars
52
Forks
—
Language
HTML
License
—
Last pushed
Feb 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/serre-lab/Lens"
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
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
ModelOriented/DALEX
moDel Agnostic Language for Exploration and eXplanation
aixplain/aiXplain
aiXplain enables python programmers to add AI functions to their software.
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...