A convex optimization toolbox using proximal splitting methods.
PyUNLocBoX is a convex optimization toolbox using proximal splitting methods implemented in Python. It is a free software distributed under the BSD license and is a port of the Matlab UNLocBoX toolbox.
Documentation : http://pyunlocbox.readthedocs.org
PyPI package : https://pypi.python.org/pypi/pyunlocbox
Travis continuous integration : https://travis-ci.org/epfl-lts2/pyunlocbox
UNLocBoX matlab toolbox : http://unlocbox.sourceforge.net
Forward-backward splitting algorithm
Douglas-Rachford splitting algorithm
Projection on the L2-ball
PyUnLocBox is continuously tested with Python 2.6, 2.7, 3.2, 3.3 and 3.4.
$ pip install pyunlocbox
Installation in an isolated virtual environment:
$ mkvirtualenv --system-site-packages pyunlocbox $ pip install pyunlocbox
You need virtualenvwrapper to run this command. The --system-site-packages option could be useful if you want to use a shared system installation of numpy and matplotlib. Their building and installation require quite some dependencies.
Another way is to manually download from PyPI, unpack the package and install with:
$ python setup.py install
Execute the project test suite once to make sure you have a working install:
$ python setup.py test
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.