Bundle ONNX Runtime inference library for running pre-trained models. Supports object detection (YOLO), image classification (ResNet), segmentation (DeepLab), pose estimation (OpenPose), face recognition, and Phi-3 text generation. Compile with -lib onnx.
FaceDetection
Single face detection result from SCRFD, containing the bounding box, confidence score, and five facial landmarks.
Operations
GetBounds #
Bounding box in original image coordinates.
method : public : GetBounds() ~ RectReturn
| Type | Description |
|---|---|
| Rect | bounding rectangle |
GetLandmarks #
Five facial landmarks as flat array [x0,y0, x1,y1, x2,y2, x3,y3, x4,y4]: left-eye, right-eye, nose, left-mouth, right-mouth.
method : public : GetLandmarks() ~ Float[]Return
| Type | Description |
|---|---|
| Float | landmark array (10 floats) |