Metadata-Version: 2.1
Name: focal-loss
Version: 0.0.1
Summary: TensorFlow implementation of focal loss.
Home-page: https://github.com/artemmavrin/focal-loss
Author: Artem Mavrin
Author-email: artemvmavrin@gmail.com
License: Apache 2.0
Description: ==========
        Focal Loss
        ==========
        
        .. image:: https://img.shields.io/pypi/pyversions/focal-loss
            :target: https://pypi.org/project/focal-loss
            :alt: Python Version
        
        .. image:: https://img.shields.io/pypi/v/focal-loss
            :target: https://pypi.org/project/focal-loss
            :alt: PyPI Package Version
        
        .. image:: https://travis-ci.com/artemmavrin/focal-loss.svg?branch=master
            :target: https://travis-ci.com/artemmavrin/focal-loss
            :alt: Build Status
        
        .. image:: https://codecov.io/gh/artemmavrin/focal-loss/branch/master/graph/badge.svg
            :target: https://codecov.io/gh/artemmavrin/focal-loss
            :alt: Code Coverage
        
        .. image:: https://readthedocs.org/projects/focal-loss/badge/?version=latest
            :target: https://focal-loss.readthedocs.io/en/latest/?badge=latest
            :alt: Documentation Status
        
        .. image:: https://img.shields.io/github/license/artemmavrin/focal-loss
            :target: https://github.com/artemmavrin/focal-loss/blob/master/LICENSE
            :alt: License
        
        TensorFlow implementation of focal loss [1]_: a loss function generalizing
        binary cross-entropy loss that penalizes hard-to-classify examples.
        
        The ``focal_loss`` package provides a function ``binary_focal_loss`` and a class
        ``BinaryFocalLoss`` that can be used as stand-in replacements for
        ``tf.keras.losses`` functions and classes, respectively.
        
        .. code-block:: python
        
            # Typical tf.keras API usage
            import tensorflow as tf
            from focal_loss import BinaryFocalLoss
        
            model = tf.keras.Model(...)
            model.compile(
                optimizer=...,
                loss=BinaryFocalLoss(gamma=2)
                metrics=...,
            )
            history = model.fit(...)
        
        .. image:: docs/source/images/focal-loss.png
            :alt: Focal loss plot
        
        Installation
        ------------
        
        1.  Make sure that a CPU or GPU version of TensorFlow 2.0 or later is installed
            (see `this link <https://www.tensorflow.org/install>`__ for installation
            instructions).
        
        2.  The ``focal_loss`` package can be installed using the
            `pip <https://pip.pypa.io/en/stable/>`__ utility. For the latest version,
            install directly from the package's
            `GitHub page <https://github.com/artemmavrin/focal-loss>`__:
        
            .. code-block:: bash
        
                pip install git+https://github.com/artemmavrin/focal-loss.git
        
            Alternatively, install the a recent release from the
            `Python Package Index (PyPI) <https://pypi.org/project/focal-loss>`__:
        
            .. code-block:: bash
        
                pip install focal-loss
        
            .. note::
        
                To install the project for development (e.g., to make changes to the
                source code), clone the project repository from GitHub and run
                :code:`make dev`:
        
                .. code-block:: bash
        
                    git clone https://github.com/artemmavrin/focal-loss.git
                    cd focal-loss
                    make dev
        
                This will additionally install the requirements needed
                to run tests, check code coverage, and produce documentation.
        
        References
        ----------
        
        .. [1] T. Lin, P. Goyal, R. Girshick, K. He and P. Dollár. Focal loss for dense
            object detection. IEEE Transactions on Pattern Analysis and Machine
            Intelligence, 2018. (`DOI <https://doi.org/10.1109/TPAMI.2018.2858826>`__)
            (`arXiv preprint <https://arxiv.org/abs/1708.02002>`__)
        
Platform: UNKNOWN
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Description-Content-Type: text/x-rst
Provides-Extra: dev
