nikitadurasov/masksembles

Official repository for the paper "Masksembles for Uncertainty Estimation" (CVPR 2021).

56
/ 100
Established

When you're building systems that rely on artificial intelligence, it's crucial to understand how confident your AI model is in its predictions, especially for critical tasks like medical diagnosis or self-driving cars. This tool helps AI practitioners get reliable uncertainty estimates from their neural networks without needing to train multiple models, which saves a lot of time and computational resources. It takes your existing deep learning model and adds a special layer, producing outputs that indicate both the prediction and its associated uncertainty.

103 stars. Available on PyPI.

Use this if you need to understand the reliability and confidence of your deep learning model's predictions in a resource-efficient manner.

Not ideal if your application doesn't require knowing the uncertainty of AI predictions or if you are not working with deep neural networks.

AI model reliability deep learning safety machine learning uncertainty computer vision predictive analytics
Maintenance 6 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

103

Forks

16

Language

Python

License

MIT

Last pushed

Nov 09, 2025

Commits (30d)

0

Dependencies

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nikitadurasov/masksembles"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.