kwatcharasupat/latte

Latte: Cross-framework Python Package for Evaluation of Latent-based Generative Models

33
/ 100
Emerging

Latte is a Python package designed to help researchers and practitioners evaluate how well their generative models understand and separate different underlying characteristics of the data. It takes the latent representations (internal codes) from your models and the actual attributes of your data, then outputs various metrics like Mutual Information Gap (MIG) and Smoothness. This is useful for anyone working to build or improve generative AI models for creating new data, images, or media.

No commits in the last 6 months.

Use this if you are developing or using latent-based generative models and need a standardized way to measure their disentanglement and controllability.

Not ideal if you are looking for a general-purpose machine learning library or do not work with latent variable models.

generative-ai model-evaluation deep-learning representation-learning artificial-intelligence
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

37

Forks

3

Language

Python

License

MIT

Last pushed

Jul 29, 2025

Commits (30d)

0

Get this data via API

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

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