YOLO Detection

Function: Uses deep learning methods to detect input images.

Input Parameters:

Name Type Valid Range Default Value Meaning

Image

ColorImage

None

None

Input image, requires a color image with RGB channels.

Output Parameters:

Name Type Valid Range Default Value Meaning

Detection results

DetectInstance

None

{}

Returns bounding boxes, categories, scores and polygon.

Parameter Settings:

Name Type Valid Range Default Value Meaning

Weight files

File

['.onnx']

None

Model file.

Confidence threshold

Float

[0.0, 1.0]

0.8

Detection threshold.

Enable GPU

Bool

None

False

Set whether to use the GPU for inference. If you need the computer to have a graphics environment to open, and because the onnxruntime version and the cuda version have requirements, you need to install cudnn and the corresponding version of onnxruntime-gpu according to the official requirements and the cuda version, see [link](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html).

Use opencv_dnn

Bool

None

False

Set whether to use opencv_dnn for inference, the detection results have shown that the detection will be slightly slower when this method is opened.