imgaug
======

`imgaug` is a library for image augmentation in machine learning experiments.
It supports a wide range of augmentation techniques, allows to easily combine
these and to execute them in random order or on multiple CPU cores,
has a simple yet powerful stochastic interface and can not only augment images,
but also keypoints/landmarks, bounding boxes, heatmaps and segmentation maps.

.. figure:: images/examples_basics/heavy.jpg
    :alt: Heavy augmentations

    Example augmentations of a single input image.

.. toctree::
   :maxdepth: 2
   :caption: Contents:

   source/installation
   source/examples_basics
   source/examples_keypoints
   source/examples_bounding_boxes
   source/examples_heatmaps
   source/examples_segmentation_maps
   source/parameters
   source/alpha
   source/overview_of_augmenters
   source/performance
   source/dtype_support
   source/jupyter_notebooks
   source/api
   source/readme_images

See :ref:`modindex` for API.

Indices and tables
==================

* :ref:`genindex`
* :ref:`modindex`
* :ref:`search`