kwatcharasupat/latte
Latte: Cross-framework Python Package for Evaluation of Latent-based Generative Models
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.
Stars
37
Forks
3
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
optuna/optuna
A hyperparameter optimization framework
keras-team/keras-tuner
A Hyperparameter Tuning Library for Keras
KernelTuner/kernel_tuner
Kernel Tuner
syne-tune/syne-tune
Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
deephyper/deephyper
DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning