You can clone with
Cannot retrieve contributors at this time
A Maximum Entropy Modeling Toolkit for Python and C++=====================================================http://homepages.inf.ed.ac.uk/lzhang10/maxent.htmlWhat is this?-------------This package provides a (Conditional) Maximum Entropy Modeling Toolkit forPython and C++. The library is written in ISO C++ and has been tested underGNU/Linux, FreeBSD/NetBSD and Win32 (Cygwin and http://www.mingw.org[MinGW]).There is also a python extension module (maxent module) available.For more information, please have a look at the file manual.pdf in doc/directory. The PDF document talks about the toolkit at length.Building--------See file INSTALL for detail description of building the maxent package on unixplatforms. Instruction on building under win32 environment is covered in thePDF manual in doc/.python/ directory contains source code for python binding of the toolkit. Thedetail instruction on building the python extension is given in python/README.License-------This software is freeware and is released under LGPL. see LICENSE file formore information. The adoption of LGPL is in accord with the license of java maxent project:http://maxent.sf.net, from which the toolkit was derived. LGPL makes iteasier to share source code, as well as new ideas, between both projects.Misc Info---------About Feature Value~~~~~~~~~~~~~~~~~~~Since binary feature and integer feature are more common than high precisionreal feature, all feature values are represented as float (4 bytes) ratherthan double (8 bytes) in order to save memory. If you need to specify doublefeature values you can find all floats in source code and replace them withdouble (require more memory).Undocumented Functions~~~~~~~~~~~~~~~~~~~~~~There are some functions in the source code that are not documented. They areconsidered experimental and are very likely to be changed in future releases. Please do not report them as bugs.Contact Author--------------Le Zhang <mailto:firstname.lastname@example.org> http://homepages.inf.ed.ac.uk/lzhang10/Question and suggestion are always welcome.