Skip to main content

An AI powered nudity detection library

Project description

ifnude

It is a nudity detection library that actually works, on both on humans and drawings.. It tells you exactly what NSFW parts of the body are visible. Optionally, you can censor the said parts.

Installation

pip install ifnude

Example

from ifnude import detect

# use mode="fast" for x3 speed with slightly lower accuracy
print(detect('/path/to/nsfw.png'))

Output

[{'box': [164, 188, 246, 271], 'score': 0.8253238201141357, 'label': 'EXPOSED_BREAST_F'}, {'box': [252, 190, 335, 270], 'score': 0.8235630989074707, 'label': 'EXPOSED_BREAST_F'}]

Credits

This is fork of NudeNet library which doesn't work anymore. I have taken the liberty to remove the video detection functionality as it was prone to crashes. It will be re-implemented in future.

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

ifnude-0.0.3.tar.gz (6.9 kB view details)

Uploaded Source

Built Distribution

ifnude-0.0.3-py2.py3-none-any.whl (7.1 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file ifnude-0.0.3.tar.gz.

File metadata

  • Download URL: ifnude-0.0.3.tar.gz
  • Upload date:
  • Size: 6.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.3

File hashes

Hashes for ifnude-0.0.3.tar.gz
Algorithm Hash digest
SHA256 5d34c6a6d7a56d1de4882c33b56922ebd956bfb0a18a9606266baabbdf457e74
MD5 a2dd51b6a67fb5c02ccc1c42d27c5e50
BLAKE2b-256 4c02895b4b9670b9ddfe6eb8afe19f9f804cb4d03c4b952f6c81bfd95716d015

See more details on using hashes here.

File details

Details for the file ifnude-0.0.3-py2.py3-none-any.whl.

File metadata

  • Download URL: ifnude-0.0.3-py2.py3-none-any.whl
  • Upload date:
  • Size: 7.1 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.3

File hashes

Hashes for ifnude-0.0.3-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 add0122d65dd1dad8232175426ca0cbe1c265a5fb7c341212648aef1bd17b9cb
MD5 8c4c7c76ed3538e6759a8b277d2dd6e3
BLAKE2b-256 cf33f574d30776de4729dc67be79b273cbd000ce37deb4b897331c0dd2a41096

See more details on using hashes here.

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