Metadata-Version: 2.1
Name: imgaug-denk
Version: 0.4.6
Summary: Image augmentation library for deep neural networks
Home-page: https://github.com/marcown/imgaug
Download-URL: https://github.com/marcown/imgaug/archive/0.4.6.tar.gz
Author: Alexander Jung
Author-email: kontakt@ajung.name
License: MIT
Keywords: augmentation,image,deep learning,neural network,CNN,machine learning,computer vision,overfitting
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.4
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Topic :: Software Development :: Libraries :: Python Modules
License-File: LICENSE
Requires-Dist: six
Requires-Dist: numpy >=1.15
Requires-Dist: scipy
Requires-Dist: Pillow
Requires-Dist: matplotlib
Requires-Dist: scikit-image >=0.14.2
Requires-Dist: opencv-python-headless
Requires-Dist: Shapely
Requires-Dist: imageio <=2.6.1 ; python_version < "3.5"
Requires-Dist: imageio ; python_version >= "3.5"

A library for image augmentation in machine learning experiments, particularly convolutional
neural networks. Supports the augmentation of images, keypoints/landmarks, bounding boxes, heatmaps and segmentation
maps in a variety of different ways.
