ultralytics/examples/YOLOv8-ONNXRuntime-CPP/README.md

YOLOv8 OnnxRuntime C++

This example demonstrates how to perform inference using YOLOv8 in C++ with ONNX Runtime and OpenCV's API.

Benefits

• Friendly for deployment in the industrial sector.
• Faster than OpenCV's DNN inference on both CPU and GPU.
• Supports FP32 and FP16 CUDA acceleration.

Exporting YOLOv8 Models

To export YOLOv8 models, use the following Python script:

from ultralytics import YOLO

# Load a YOLOv8 model
model = YOLO("yolov8n.pt")

# Export the model
model.export(format="onnx", opset=12, simplify=True, dynamic=False, imgsz=640)

Alternatively, you can use the following command for exporting the model in the terminal

yolo export model=yolov8n.pt opset=12 simplify=True dynamic=False format=onnx imgsz=640,640

Dependencies

Dependency	Version
Onnxruntime(linux,windows,macos)	>=1.14.1
OpenCV	>=4.0.0
C++	>=17
Cmake	>=3.5

Note: The dependency on C++17 is due to the usage of the C++17 filesystem feature.

Usage

// CPU inference
DCSP_INIT_PARAM params{ model_path, YOLO_ORIGIN_V8, {imgsz_w, imgsz_h}, 0.1, 0.5, false};
// GPU inference
DCSP_INIT_PARAM params{ model_path, YOLO_ORIGIN_V8, {imgsz_w, imgsz_h}, 0.1, 0.5, true};
// Load your image
cv::Mat img = cv::imread(img_path);
// Init Inference Session
char* ret = yoloDetector->CreateSession(params);

ret = yoloDetector->RunSession(img, res);

This repository should also work for YOLOv5, which needs a permute operator for the output of the YOLOv5 model, but this has not been implemented yet.