Skip to main content

This package provides a set of image corruptions.

Project description

imagecorruptions

This package provides a set of corruptions that can be applied to images in order to benchmark the robustness of neural networks. These corruptions are not meant to be used as training data augmentation but rather to test the networks against unseen perturbations. For more information have a look at the paper on the original corruption package by Hendrycks and Dietterich: Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations.

image corruptions

Installation and Usage

This package is pip installable via pip3 install imagecorruptions. An example of how to use the corruption function is given below:

from imagecorruptions import corrupt
...
corrupted_image = corrupt(image, corruption_name='gaussian_blur', severity=1)
...

Looping over all available corruptions can be done either by name or by index:

# via name
from imagecorruptions import get_corruption_names
for corruption in get_corruption_names():
    for severity in range(5):
        corrupted = corrupt(image, corruption_name=corruption, severity=severity+1)
        ...

# via number:
for i in range(15):
    for severity in range(5):
        corrupted = corrupt(image, corruption_number=i, severity=severity+1)
        ...

Note that the first 15 image corruptions are the common corruptions (the ones you get via get_corruption_names()). If you really wish to use these as data augmentation, there exist four additional validation corruptions which can be accessed via get_corruption_names('validation') which should then be used to test the corruption robustness of the trained model.

Citation

If you use our code or the imagecorruptions package, please consider citing:

@article{michaelis2019dragon,
  title={Benchmarking Robustness in Object Detection: 
    Autonomous Driving when Winter is Coming},
  author={Michaelis, Claudio and Mitzkus, Benjamin and 
    Geirhos, Robert and Rusak, Evgenia and 
    Bringmann, Oliver and Ecker, Alexander S. and 
    Bethge, Matthias and Brendel, Wieland},
  journal={arXiv preprint arXiv:1907.07484},
  year={2019}
}

Credit and Changelog

This package is an extension of the image corruption functions provided by Dan Hendrycks in the repository corruptions. The image corruptions implemented by Hendrycks are generalized to work on images with arbitrary image dimensions and aspect ratios aswell as on grayscale images. We furthermore removed the dependency to libmagickwand and the python api Wand and reimplemented the motion_blur in python.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

imagecorruptions-1.1.2.tar.gz (2.1 MB view details)

Uploaded Source

Built Distribution

imagecorruptions-1.1.2-py3-none-any.whl (2.1 MB view details)

Uploaded Python 3

File details

Details for the file imagecorruptions-1.1.2.tar.gz.

File metadata

  • Download URL: imagecorruptions-1.1.2.tar.gz
  • Upload date:
  • Size: 2.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.53.0 CPython/3.8.5

File hashes

Hashes for imagecorruptions-1.1.2.tar.gz
Algorithm Hash digest
SHA256 044e173f24d5934899bdbf3596bfbec917e8083e507eed583ab217abebbe084d
MD5 f8b0c29ec4f791b8857f84f25a13019f
BLAKE2b-256 22810e89d4524064b683cb3b0b5c5874e41307d730c473673051d3c68d52605f

See more details on using hashes here.

File details

Details for the file imagecorruptions-1.1.2-py3-none-any.whl.

File metadata

  • Download URL: imagecorruptions-1.1.2-py3-none-any.whl
  • Upload date:
  • Size: 2.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.53.0 CPython/3.8.5

File hashes

Hashes for imagecorruptions-1.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 d0e4bf529ba6fbb27d8aba1bde7c5db43bf2b969b2c767c11419e939e3e365b8
MD5 9311416fb21be0bf95ef30207c3905d7
BLAKE2b-256 3e40ff4a79ad7ab6463fe2fde7912b71084a6606e33676078a50b40a3377112b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page