Skip to content

Latest commit

 

History

History
30 lines (22 loc) · 790 Bytes

README.md

File metadata and controls

30 lines (22 loc) · 790 Bytes

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