# Ultra Light
Ultra Light Fast Generic Face Detector ๐จโ๐ฉโ๐งโ๐ฆ๐ผ
![sample](samples/sample_detected.jpg)
Very fast and quality face detector. Can use CPU, GPU and MPS (Apple M1 ML) providers.
Work via ONNX model
## Installation
```bash
pip install ultralight
```
## Usage sample
```python
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](samples/sample.py)
## Reference
[GitHub repository of original detector](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB)
[ArXiv paper of original detector](https://arxiv.org/pdf/1905.00641.pdf)
## 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)
Raw data
{
"_id": null,
"home_page": "https://github.com/abionics/UltraLight",
"name": "ultralight",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "face detection ai ultra light",
"author": "Alex Ermolaev",
"author_email": "abionics.dev@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/5a/0b/02612654e972a90d733df209badabb7ad38af8718bb2e6cdc6e12fd53d50/ultralight-2.2.0.tar.gz",
"platform": null,
"description": "# Ultra Light\n\nUltra Light Fast Generic Face Detector \ud83d\udc68\u200d\ud83d\udc69\u200d\ud83d\udc67\u200d\ud83d\udc66\ud83d\uddbc\n\n![sample](samples/sample_detected.jpg)\n\nVery fast and quality face detector. Can use CPU, GPU and MPS (Apple M1 ML) providers.\nWork via ONNX model\n\n\n## Installation\n\n```bash\npip install ultralight\n```\n\n\n## Usage sample\n\n```python\nimport cv2\nfrom ultralight import UltraLightDetector\nfrom ultralight.utils import draw_faces\n\nimage = cv2.imread('sample.jpg')\n\ndetector = UltraLightDetector()\nboxes, scores = detector.detect_one(image)\nprint(f'Found {len(boxes)} face(s)')\n# >>> Found 14 face(s)\n\ndraw_faces(image, boxes, scores)\ncv2.imshow('result', image)\ncv2.waitKey(0)\n```\n\nThis sample can be found [here](samples/sample.py)\n\n\n## Reference\n\n[GitHub repository of original detector](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB)\n\n[ArXiv paper of original detector](https://arxiv.org/pdf/1905.00641.pdf)\n\n\n## More\n\nPyPI: https://pypi.org/project/ultralight\n\nRepository: https://github.com/abionics/UltraLight\n\nDeveloper: Alex Ermolaev (Abionics)\n\nEmail: abionics.dev@gmail.com\n\nLicense: MIT (see LICENSE.txt)\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Ultra Light Fast Generic Face Detector \ud83d\udc68\u200d\ud83d\udc69\u200d\ud83d\udc67\u200d\ud83d\udc66\ud83d\uddbc",
"version": "2.2.0",
"project_urls": {
"Homepage": "https://github.com/abionics/UltraLight"
},
"split_keywords": [
"face",
"detection",
"ai",
"ultra",
"light"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5a0b02612654e972a90d733df209badabb7ad38af8718bb2e6cdc6e12fd53d50",
"md5": "afd23089a067e884a98411ae6aaa9151",
"sha256": "f6e5e0e7c638bb6ea76a0f87dba20e792484aba0667a8f78a80effcacee1c67f"
},
"downloads": -1,
"filename": "ultralight-2.2.0.tar.gz",
"has_sig": false,
"md5_digest": "afd23089a067e884a98411ae6aaa9151",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 8041,
"upload_time": "2023-12-25T12:09:56",
"upload_time_iso_8601": "2023-12-25T12:09:56.669568Z",
"url": "https://files.pythonhosted.org/packages/5a/0b/02612654e972a90d733df209badabb7ad38af8718bb2e6cdc6e12fd53d50/ultralight-2.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-25 12:09:56",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "abionics",
"github_project": "UltraLight",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "ultralight"
}