Skip to main content

Copyout and CopyPaiting Image Augmentation

Project description

COOCOP - Copyout and CopyPaiting implementation

This is an implementation of the Copyout and CopyPairing image augmentation techniques. The paper about this can be found here: Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing

Installation

Install or update with pip:

pip install coocop -U

Install development version:

pip install git+https://github.com/t-systems-on-site-services-gmbh/coocop.git -U

Citation / BibTeX

This is how you can cite this work with LaTeX / BibTeX:

@article{Copyout,
title = "{Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing}",
author = {Philip May},
journal = {arXiv.org},
year = "2019",
archivePrefix = {arXiv},
eprint = {arXiv:1909.00390 [cs.CV]},
url = {https://arxiv.org/abs/1909.00390},
}

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

coocop-0.2.tar.gz (2.9 kB view details)

Uploaded Source

Built Distribution

coocop-0.2-py3-none-any.whl (4.0 kB view details)

Uploaded Python 3

File details

Details for the file coocop-0.2.tar.gz.

File metadata

  • Download URL: coocop-0.2.tar.gz
  • Upload date:
  • Size: 2.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.15.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.35.0 CPython/3.6.9

File hashes

Hashes for coocop-0.2.tar.gz
Algorithm Hash digest
SHA256 e9136fff5c61bfe7376b5933ac26a0c6603efd631e8e00f8e9c654a95d2e14d0
MD5 e296eda9566a29b065c567e1b91624c0
BLAKE2b-256 4adfe1f9a5eda0ecc21bcdf195aff7623caf3900093f3cc9a353fea3837aa240

See more details on using hashes here.

Provenance

File details

Details for the file coocop-0.2-py3-none-any.whl.

File metadata

  • Download URL: coocop-0.2-py3-none-any.whl
  • Upload date:
  • Size: 4.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.15.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.35.0 CPython/3.6.9

File hashes

Hashes for coocop-0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 2b5eeb3cd5166edd311a5ffddb97b62d21a604eb2f036c5314db6d6fec65b134
MD5 6898e1edb0cecae315cda0f07d0074e6
BLAKE2b-256 fab13542b68c7561490443ab730b184d89e8b6e2539f12817ff645f2268a3137

See more details on using hashes here.

Provenance

Supported by

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