Skip to content
/ smolcde Public

Small lib/cli for conditional density estimation

Notifications You must be signed in to change notification settings

maedoc/smolcde

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

smolcde

A small library for conditional density estimation using masked autoregressive flows, with Python & C implementations and a small CLI.

Setup

The CLI/C implementation, is usable from source via clone repo & cmake . && make, otherwise download from releases on GitHub, where binaries for each platform are available.

The Python implementation depends on numpy, scipy and autograd only, making it easy to just drop the file cde.py into your project.

You can run the tests with Python

uv venv env; . env/bin/activate
uv pip install pytest scipy autograd scikit_learn tqdm
pytest

Usage examples

Please see README.ipynb for info on usage & examples.

About

Small lib/cli for conditional density estimation

Resources

Stars

Watchers

Forks