Skip to main content

Efficient face detection using SCRFD onnxruntime inference

Project description

SCRFD

github

Efficient face detection using SCRFD onnxruntime inference.

Requires python >= 3.10

pip install scrfd
from scrfd import SCRFD, Threshold
from PIL import Image

face_detector = SCRFD.from_path("./models/scrfd.onnx")
threshold = Threshold(probability=0.4)

image = Image.open("./images/solvay_conference_1927.jpg")
faces = face_detector.detect(image, threshold=threshold)

for face in faces:
    bbox = face.bbox
    kps = face.keypoints
    score = face.probability
    print(f"{bbox=}, {kps=}, {score=}")
face detection

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

scrfd-0.2.1.tar.gz (8.3 kB view details)

Uploaded Source

Built Distribution

scrfd-0.2.1-py3-none-any.whl (9.5 kB view details)

Uploaded Python 3

File details

Details for the file scrfd-0.2.1.tar.gz.

File metadata

  • Download URL: scrfd-0.2.1.tar.gz
  • Upload date:
  • Size: 8.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.11.5 Darwin/22.1.0

File hashes

Hashes for scrfd-0.2.1.tar.gz
Algorithm Hash digest
SHA256 9d93b165a162e32e2b22d42b345e190a0292a429f38a0678fffc92fef1dde5a0
MD5 88125051268fb2376590a617b829be5d
BLAKE2b-256 37fe4abf9d6c9f893f30bb57b238f707807ea8e18fcff12e9493e0f73204c891

See more details on using hashes here.

File details

Details for the file scrfd-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: scrfd-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 9.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.11.5 Darwin/22.1.0

File hashes

Hashes for scrfd-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 71dcbe334860361ad3e543c7375b86d0903517e43b6a927c8da3d737bcee93cc
MD5 4f8e50c3a760e81c2d2bb83d64ab873b
BLAKE2b-256 4f30640e76dcec55dca403410f2620800b40987ec3fcb2a5d8c959cbb4ef1de0

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