Skip to main content

Ultra Light Fast Generic Face Detector 👨‍👩‍👧‍👦🖼

Project description

Ultra Light

Ultra Light Fast Generic Face Detector 👨‍👩‍👧‍👦🖼

sample

Very fast and quality face detector. Can use CPU, GPU and MPS (Apple M1 ML) providers. Work via ONNX model

Installation

pip install ultralight

Usage sample

import cv2
from ultralight import UltraLightDetector
from ultralight.utils import draw_faces

image = cv2.imread('sample.jpg')

detector = UltraLightDetector()
boxes, scores = detector.detect_one(image)
print(f'Found {len(boxes)} face(s)')
# >>> Found 14 face(s)

draw_faces(image, boxes, scores)
cv2.imshow('result', image)
cv2.waitKey(0)

This sample can be found here

Reference

GitHub repository of original detector

ArXiv paper of original detector

More

PyPI: https://pypi.org/project/ultralight

Repository: https://github.com/abionics/UltraLight

Developer: Alex Ermolaev (Abionics)

Email: abionics.dev@gmail.com

License: MIT (see LICENSE.txt)

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

ultralight-2.1.0.tar.gz (8.0 kB view details)

Uploaded Source

File details

Details for the file ultralight-2.1.0.tar.gz.

File metadata

  • Download URL: ultralight-2.1.0.tar.gz
  • Upload date:
  • Size: 8.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for ultralight-2.1.0.tar.gz
Algorithm Hash digest
SHA256 9e3bb5b46b3ba4b8badbca5d8230a26ad30c5eec428d4494631a1d13dd22e6a8
MD5 4d574fb12a28edbda916e63dcc3247a4
BLAKE2b-256 7def36cd5d914f95c2290b3fd4d85564b93af003beb4b026ab324c0bd170d388

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