levmar

A Python binding to the levmar library. Note that this is a fork of https://github.com/tkanmae/levmar.

Description

The levmar is GPL'ed ANSI C implementation of the Levenberg-Marquardt (LM) optimization algorithm. The LM algorithm provides a numerical solution to the problem of minimizing a function over a parameter space of a function. The levmar library provides implementation of both unconstrained and constrained LM algorithms (box, linear equation, and linear inequality constraints).

Installation

Simplest way to install levmar and its dependencies is to use the conda package manager:

$ conda install -c bjodah levmar pytest
$ python -m pytest --pyargs levmar  # runs the test-suite

alternatively you may also use pip:

$ python -m pip install --user --upgrade pytest levmar
$ python -m pytest --pyargs levmar

you can skip the --user flag if you have got root permissions.

Documentation

See docstrings and demo scripts contained in the directory ./examples. Documentation of the levmar library can be found at http://www.ics.forth.gr/~lourakis/levmar/. Auto-generated API documentation for the latest stable release of this wrapper is found here: https://bjodah.github.io/levmar/latest (and the development version for the current master branch of this wrapper is found here: http://hera.physchem.kth.se/~levmar/branches/master/html).

Authors

Takeshi Kanmae <tkanmae@gmail.com>. For all authors see AUTHORS.

License

The MIT license applies to all the files except those in ./levmar-2.6. All of the software in ./levmar-2.6 and only the software therein is copyrighted by Manolis Lourakis and is licensed under the terms and conditions of the GNU General Public License (GPL). See the file LICENSE.txt.

Resources

• levmar: http://www.ics.forth.gr/~lourakis/levmar/
• Python: http://www.python.org/
• NumPy: http://www.scipy.org/
• nose: http://somethingaboutorange.com/mrl/projects/nose
• Cython: http://www.cython.org/