Metadata-Version: 1.2
Name: disentangle
Version: 0.0.4
Summary: Quickly create disentanglement pipelines for machine learning research.
Home-page: https://github.com/yukunchen113/disentangle
Author: Yukun Chen
Author-email: yukunchenlib@gmail.com
License: MIT
Project-URL: Documentation, https://disentangle.readthedocs.io/
Project-URL: Changelog, https://disentangle.readthedocs.io/en/latest/changelog.html
Project-URL: Issue Tracker, https://github.com/yukunchen113/disentangle/issues
Description: ========
        Overview
        ========
        
        
        
        Quickly create disentanglement pipelines for machine learning research.
        
        This has prebuilt and functionality for tensorflow function wrappers, to make changing the architecture easy. Though it is not too hard to use keras, viewing the whole architecture on one page and making comparisons between different archtectures might be a bit of a pain and prone to errors. 
        
        Though this library can be used to wrap any tensorflow (or custom) keras module, making it useful for a variety of different fields of deep learning research. This library is called disentangle as my main focus of research is on disentanglement and much of the functionality (such as visualization tools, prebuilt architectures, etc) are biased towards that.
        
        There are a few parts of this which use functionality from disentanglement_lib, so please take a look at their work. This code is contained in other_library_tools.
        
        Other than tensorflow wrappers, this library contains useful functionality for datasets (custom, if needed), visualizations, and general useful tools such as timers and path managers.
        
        Thanks to ionelmc's cookiecutter-pylibrary for the generation of a pypi library with many good practices. So I could easily convert this library to be deployable to pypi.
        
        * Free software: MIT license
        
        Installation
        ============
        
        ::
        
            pip install disentangle
        
        You can also install the in-development version with::
        
            pip install https://github.com/yukunchen113/disentangle/archive/master.zip
        
        
        Documentation
        =============
        
        
        https://disentangle.readthedocs.io/
        
        
        Development
        ===========
        
        To run all the tests run::
        
            tox
        
        Note, to combine the coverage data from all the tox environments run:
        
        .. list-table::
            :widths: 10 90
            :stub-columns: 1
        
            - - Windows
              - ::
        
                    set PYTEST_ADDOPTS=--cov-append
                    tox
        
            - - Other
              - ::
        
                    PYTEST_ADDOPTS=--cov-append tox
        
        
        Changelog
        =========
        
        0.0.0 (2020-08-16)
        ------------------
        
        * First release on PyPI.
        
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: Unix
Classifier: Operating System :: POSIX
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Utilities
Requires-Python: >=3.6, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*
