Metadata-Version: 2.1
Name: MixtureLib
Version: 0.1.2
Summary: mixture lib, python package
Home-page: https://github.com/andriygav/MixtureLib
Author: Andrey Grabovoy
Author-email: grabovoy.av@phystech.edu
License: MIT
Platform: UNKNOWN
Requires-Python: ==3.6.*
Requires-Dist: torch (>=1.3.1+cpu)
Requires-Dist: numpy (>=1.18.1)

###########
Mixture Lib
###########

|test| |docs|

.. |test| image:: 	https://github.com/andriygav/MixtureLib/workflows/test/badge.svg
    :target: https://github.com/andriygav/MixtureLib/tree/master
    :alt: Build status

.. |docs| image:: 	https://github.com/andriygav/MixtureLib/workflows/docs/badge.svg
    :target: https://github.com/andriygav/MixtureLib/tree/master
    :alt: Build status

Basic information
=================

Implementation code for a mixture of models. The `source code <https://github.com/andriygav/MixtureLib/tree/master/src>`_ for the problem of the mixture of models and the task of the mixture of experts is presented.

All methods were implemented based on ``pytorch`` for simple parallelization by using ``cuda``.

All information about this project can be found in the `documentation <https://andriygav.github.io/MixtureLib/>`_.

Requirements and Installation
=============================
A simple instruction of installation using pip is provided near the `source code <https://github.com/andriygav/MixtureLib/tree/master/src>`_.

More information about installation can be found in documentation `installation <https://andriygav.github.io/MixtureLib/installation.html>`_ page.

Example of use
==============
A simple examples of module usage can be found in documentation `example <file:///Users/andrey/MixtureLib/public/example.html>`_ page.




