Skip to main content

This library detects nsfw objects and body parts in images and videos and optionally censores them.

Project description

NSFW Recog

This library is meant to detect and censor nsfw content in public media. Models can be found here, they are downloaded automatically and cached.

sample image

Installation

  • install requirements.txt
  • install pytorch according to your cuda version
  • (optional) install onnxruntime-gpu to support cuda usage

Usage

Instantiate a NsfwDetector class and use the methods detect(), blur(), video() and camera(). The demos show the usage:

  • demo_detect.py: Detecting body parts/objects in an image
  • demo_camera.py: Live detecting objects in a webcam stream
  • demo_video.py: Detecting objects in a video and draw bounding boxes and labels to a new video
  • demo_blur.py: Detecting objects in an image and blurring them.

Project details


Release history Release notifications | RSS feed

This version

1.0

Download files

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

Source Distribution

nsfwrecog-1.0.tar.gz (8.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nsfwrecog-1.0-py3-none-any.whl (8.6 kB view details)

Uploaded Python 3

File details

Details for the file nsfwrecog-1.0.tar.gz.

File metadata

  • Download URL: nsfwrecog-1.0.tar.gz
  • Upload date:
  • Size: 8.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for nsfwrecog-1.0.tar.gz
Algorithm Hash digest
SHA256 736bcd2152b33e1011b5ee13b67440b6d0112159e41369371caa59bb467da28f
MD5 b91f05c9f2c1e983c594b264dbf11490
BLAKE2b-256 81e60a82e172482f23920bb087db3378fa1342ead6d9e5d7ef94812839e3d32d

See more details on using hashes here.

File details

Details for the file nsfwrecog-1.0-py3-none-any.whl.

File metadata

  • Download URL: nsfwrecog-1.0-py3-none-any.whl
  • Upload date:
  • Size: 8.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for nsfwrecog-1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f64194d4feecbfaa6916f0446ccc41db793bac648bcab590669673c15c173bb4
MD5 319a15ea6f900df86f10f1a40e5cf553
BLAKE2b-256 90be44fc482515f04155b9f7d4eba949bd82c462d7e9ddf6cf1859abfebd6b18

See more details on using hashes here.

Supported by

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