You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
Onuralp SEZER 4885538693
🖼️ Format bbox label with fixed precision for ortcpp-example (#4409)
1 year ago
..
CMakeLists.txt 🖼️ Format bbox label with fixed precision for ortcpp-example (#4409) 1 year ago
README.md 🖼️ Format bbox label with fixed precision for ortcpp-example (#4409) 1 year ago
inference.cpp Update YOLOv8-ONNXRuntime-CPP example with GPU inference (#4328) 1 year ago
inference.h Update YOLOv8-ONNXRuntime-CPP example with GPU inference (#4328) 1 year ago
main.cpp 🖼️ Format bbox label with fixed precision for ortcpp-example (#4409) 1 year ago

README.md

YOLOv8 OnnxRuntime C++

C++ Onnx-runtime

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

Download COCO.yaml file 📂

In order to run example, you also need to download coco.yaml. You can download the file manually from here

Dependencies

Dependency Version
Onnxruntime(linux,windows,macos) >=1.14.1
OpenCV >=4.0.0
C++ Standard >=17
Cmake >=3.5
Cuda (Optional) >=11.4 <12.0
cuDNN (Cuda required) =8

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

Note (2): Due to ONNX Runtime, we need to use CUDA 11 and cuDNN 8. Keep in mind that this requirement might change in the future.

Build 🛠

  1. Clone the repository to your local machine.
  2. Navigate to the root directory of the repository.
  3. Create a build directory and navigate to it:
mkdir build && cd build
  1. Run CMake to generate the build files:
cmake ..
  1. Build the project:
make
  1. The built executable should now be located in the build directory.

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.