zhao.zhu/yolov26_3d
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

单目3D初始代码

Browse Source
This commit is contained in:
zhao.zhu
2026-06-24 09:35:46 +08:00
commit 04a5895b6b
1153 changed files with 340700 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
examples/YOLOv8-ONNXRuntime-CPP/CMakeLists.txt Executable file
View File

@@ -0,0 +1,101 @@
cmake_minimum_required(VERSION 3.5)
set(PROJECT_NAME Yolov8OnnxRuntimeCPPInference)
project(${PROJECT_NAME} VERSION 0.0.1 LANGUAGES CXX)
# -------------- Support C++17 for using filesystem ------------------#
set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_CXX_EXTENSIONS ON)
set(CMAKE_INCLUDE_CURRENT_DIR ON)
# -------------- OpenCV ------------------#
find_package(OpenCV REQUIRED)
include_directories(${OpenCV_INCLUDE_DIRS})
# -------------- Compile CUDA for FP16 inference if needed ------------------#
option(USE_CUDA "Enable CUDA support" ON)
if (NOT APPLE AND USE_CUDA)
find_package(CUDA REQUIRED)
include_directories(${CUDA_INCLUDE_DIRS})
add_definitions(-DUSE_CUDA)
else ()
set(USE_CUDA OFF)
endif ()
# -------------- ONNXRUNTIME ------------------#
# Set ONNXRUNTIME_VERSION
set(ONNXRUNTIME_VERSION 1.15.1)
if (NOT DEFINED ONNXRUNTIME_ROOT OR ONNXRUNTIME_ROOT STREQUAL "")
if (WIN32)
if (USE_CUDA)
set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-win-x64-gpu-${ONNXRUNTIME_VERSION}")
else ()
set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-win-x64-${ONNXRUNTIME_VERSION}")
endif ()
elseif (LINUX)
if (USE_CUDA)
set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-linux-x64-gpu-${ONNXRUNTIME_VERSION}")
else ()
set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-linux-x64-${ONNXRUNTIME_VERSION}")
endif ()
elseif (APPLE)
set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-osx-arm64-${ONNXRUNTIME_VERSION}")
# Apple X64 binary
# set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-osx-x64-${ONNXRUNTIME_VERSION}")
# Apple Universal binary
# set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-osx-universal2-${ONNXRUNTIME_VERSION}")
else ()
message(SEND_ERROR "Variable ONNXRUNTIME_ROOT is not set properly. Please check if your cmake project \
is not compiled with `-D WIN32=TRUE`, `-D LINUX=TRUE`, or `-D APPLE=TRUE`!")
endif ()
endif()
include_directories(${PROJECT_NAME} ${ONNXRUNTIME_ROOT}/include)
set(PROJECT_SOURCES
main.cpp
inference.h
inference.cpp
)
add_executable(${PROJECT_NAME} ${PROJECT_SOURCES})
if (WIN32)
target_link_libraries(${PROJECT_NAME} ${OpenCV_LIBS} ${ONNXRUNTIME_ROOT}/lib/onnxruntime.lib)
if (USE_CUDA)
target_link_libraries(${PROJECT_NAME} ${CUDA_LIBRARIES})
endif ()
elseif (LINUX)
target_link_libraries(${PROJECT_NAME} ${OpenCV_LIBS} ${ONNXRUNTIME_ROOT}/lib/libonnxruntime.so)
if (USE_CUDA)
target_link_libraries(${PROJECT_NAME} ${CUDA_LIBRARIES})
endif ()
elseif (APPLE)
target_link_libraries(${PROJECT_NAME} ${OpenCV_LIBS} ${ONNXRUNTIME_ROOT}/lib/libonnxruntime.dylib)
endif ()
# For windows system, copy onnxruntime.dll to the same folder of the executable file
if (WIN32)
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
COMMAND ${CMAKE_COMMAND} -E copy_if_different
"${ONNXRUNTIME_ROOT}/lib/onnxruntime.dll"
$<TARGET_FILE_DIR:${PROJECT_NAME}>)
endif ()
# Download https://raw.githubusercontent.com/ultralytics/ultralytics/main/ultralytics/cfg/datasets/coco.yaml
# and put it in the same folder of the executable file
configure_file(coco.yaml ${CMAKE_CURRENT_BINARY_DIR}/coco.yaml COPYONLY)
# Copy yolov8n.onnx file to the same folder of the executable file
configure_file(yolov8n.onnx ${CMAKE_CURRENT_BINARY_DIR}/yolov8n.onnx COPYONLY)
# Create folder name images in the same folder of the executable file
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
COMMAND ${CMAKE_COMMAND} -E make_directory ${CMAKE_CURRENT_BINARY_DIR}/images
)

173
examples/YOLOv8-ONNXRuntime-CPP/README.md Executable file
View File

@@ -0,0 +1,173 @@
# YOLOv8 ONNX Runtime C++ Example
<img alt="C++" src="https://img.shields.io/badge/C++-17-blue.svg?style=flat&logo=c%2B%2B"> <img alt="Onnx-runtime" src="https://img.shields.io/badge/OnnxRuntime-717272.svg?logo=Onnx&logoColor=white">
This example provides a practical guide on performing inference with [Ultralytics YOLOv8](https://docs.ultralytics.com/models/yolov8/) models using [C++](https://isocpp.org/), leveraging the capabilities of the [ONNX Runtime](https://onnxruntime.ai/) and the [OpenCV](https://opencv.org/) library. It's designed for developers looking to integrate YOLOv8 into C++ applications for efficient object detection.
## ✨ Benefits
- **Deployment-Friendly:** Well-suited for deployment in industrial and production environments.
- **Performance:** Offers faster [inference latency](https://www.ultralytics.com/glossary/inference-latency) compared to OpenCV's DNN module on both CPU and [GPU](https://www.ultralytics.com/glossary/gpu-graphics-processing-unit).
- **Acceleration:** Supports FP32 and [FP16 (Half Precision)](https://www.ultralytics.com/glossary/half-precision) inference acceleration using [NVIDIA CUDA](https://developer.nvidia.com/cuda-toolkit).
## ☕ Note
Thanks to recent updates in Ultralytics, YOLOv8 models now include a `Transpose` operation, aligning their output shape with YOLOv5. This allows the C++ code in this project to run inference seamlessly for YOLOv5, YOLOv7, and YOLOv8 models exported to the [ONNX format](https://onnx.ai/).
## 📦 Exporting YOLOv8 Models
You can export your trained [Ultralytics YOLO](https://docs.ultralytics.com/) models to the ONNX format required by this project. Use the Ultralytics `export` mode for this.
### Python
```python
from ultralytics import YOLO
# Load a YOLOv8 model (e.g., yolov8n.pt)
model = YOLO("yolov8n.pt")
# Export the model to ONNX format
# opset=12 is recommended for compatibility
# simplify=True optimizes the model graph
# dynamic=False ensures fixed input size, often better for C++ deployment
# imgsz=640 sets the input image size
model.export(format="onnx", opset=12, simplify=True, dynamic=False, imgsz=640)
print("Model exported successfully to yolov8n.onnx")
```
### CLI
```bash
# Export the model using the command line
yolo export model=yolov8n.pt format=onnx opset=12 simplify=True dynamic=False imgsz=640
```
For more details on exporting models, refer to the [Ultralytics Export documentation](https://docs.ultralytics.com/modes/export/).
## 📦 Exporting YOLOv8 FP16 Models
To potentially gain further performance on compatible hardware (like NVIDIA GPUs), you can convert the exported FP32 ONNX model to FP16.
```python
import onnx
from onnxconverter_common import (
float16,
) # Ensure you have onnxconverter-common installed: pip install onnxconverter-common
# Load your FP32 ONNX model
fp32_model_path = "yolov8n.onnx"
model = onnx.load(fp32_model_path)
# Convert the model to FP16
model_fp16 = float16.convert_float_to_float16(model)
# Save the FP16 model
fp16_model_path = "yolov8n_fp16.onnx"
onnx.save(model_fp16, fp16_model_path)
print(f"Model converted and saved to {fp16_model_path}")
```
## 📂 Download COCO YAML File
This example uses class names defined in a YAML file. You'll need the `coco.yaml` file, which corresponds to the standard [COCO dataset](https://docs.ultralytics.com/datasets/detect/coco/) classes. Download it directly:
- [Download coco.yaml](https://raw.githubusercontent.com/ultralytics/ultralytics/main/ultralytics/cfg/datasets/coco.yaml)
Save this file in the same directory where you plan to run the executable, or adjust the path in the C++ code accordingly.
## ⚙️ Dependencies
Ensure you have the following dependencies installed:
| Dependency | Version | Notes |
| :------------------------------------------------------------------- | :------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [ONNX Runtime](https://onnxruntime.ai/docs/install/) | >=1.14.1 | Download pre-built binaries or build from source. Ensure GPU version if using CUDA. |
| [OpenCV](https://opencv.org/releases/) | >=4.0.0 | Required for image loading and preprocessing. |
| C++ Compiler | C++17 Support | Needed for features like `<filesystem>`. ([GCC](https://gcc.gnu.org/), [Clang](https://clang.llvm.org/), [MSVC](https://visualstudio.microsoft.com/vs/features/cplusplus/)) |
| [CMake](https://cmake.org/download/) | >=3.18 | Cross-platform build system generator. Version 3.18+ recommended for better CUDA support discovery. |
| [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit) (Optional) | >=11.4, <12.0 | Required for GPU acceleration via ONNX Runtime's CUDA Execution Provider. **Must be CUDA 11.x**. |
| [cuDNN](https://developer.nvidia.com/cudnn) (CUDA required) | =8.x | Required by CUDA Execution Provider. **Must be cuDNN 8.x** compatible with your CUDA 11.x version. |
**Important Notes:**
1. **C++17:** The requirement stems from using the `<filesystem>` library introduced in C++17 for path handling.
2. **CUDA/cuDNN Versions:** ONNX Runtime's CUDA execution provider currently has strict version requirements (CUDA 11.x, cuDNN 8.x). Check the latest [ONNX Runtime documentation](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html) for any updates to these constraints. Using incompatible versions will lead to runtime errors.
## 🛠️ Build Instructions
1. **Clone the Repository:**
```bash
git clone https://github.com/ultralytics/ultralytics.git
cd ultralytics/examples/YOLOv8-ONNXRuntime-CPP
```
2. **Create Build Directory:**
```bash
mkdir build && cd build
```
3. **Configure with CMake:**
Run CMake to generate build files. You **must** specify the path to your ONNX Runtime installation directory using `ONNXRUNTIME_ROOT`. Adjust the path according to where you downloaded or built ONNX Runtime.
```bash
# Example for Linux/macOS (adjust path as needed)
cmake .. -DONNXRUNTIME_ROOT=/path/to/onnxruntime
# Example for Windows (adjust path as needed, use backslashes or forward slashes)
cmake .. -DONNXRUNTIME_ROOT="C:/path/to/onnxruntime"
```
**CMake Options:**
- `-DONNXRUNTIME_ROOT=<path>`: **(Required)** Path to the extracted ONNX Runtime library.
- `-DCMAKE_BUILD_TYPE=Release`: (Optional) Build in Release mode for optimizations.
- If CMake struggles to find OpenCV, you might need to set `-DOpenCV_DIR=/path/to/opencv/build`.
4. **Build the Project:**
Use the build tool generated by CMake (e.g., Make, Ninja, Visual Studio).
```bash
# Using Make (common on Linux/macOS)
make
# Using CMake's generic build command (works with Make, Ninja, etc.)
cmake --build . --config Release
```
5. **Locate Executable:**
The compiled executable (e.g., `yolov8_onnxruntime_cpp`) will be located in the `build` directory.
## 🚀 Usage
Before running, ensure:
- The exported `.onnx` model file (e.g., `yolov8n.onnx`) is accessible.
- The `coco.yaml` file is accessible.
- Any required shared libraries for ONNX Runtime and OpenCV are in the system's PATH or accessible by the executable.
Modify the `main.cpp` file (or create a configuration mechanism) to set the parameters:
```cpp
//change your param as you like
//Pay attention to your device and the onnx model type(fp32 or fp16)
DL_INIT_PARAM params;
params.rectConfidenceThreshold = 0.1;
params.iouThreshold = 0.5;
params.modelPath = "yolov8n.onnx";
params.imgSize = { 640, 640 };
params.cudaEnable = true;
params.modelType = YOLO_DETECT_V8;
yoloDetector->CreateSession(params);
Detector(yoloDetector);
```
Run the executable from the `build` directory:
```bash
./yolov8_onnxruntime_cpp
```
## 🤝 Contributing
Contributions are welcome! If you find any issues or have suggestions for improvements, please feel free to open an issue or submit a pull request on the main [Ultralytics repository](https://github.com/ultralytics/ultralytics).

374
examples/YOLOv8-ONNXRuntime-CPP/inference.cpp Executable file
View File

@@ -0,0 +1,374 @@
// Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
#include "inference.h"
#include <regex>
#define benchmark
#define min(a,b) (((a) < (b)) ? (a) : (b))
YOLO_V8::YOLO_V8() {
}
YOLO_V8::~YOLO_V8() {
delete session;
}
#ifdef USE_CUDA
namespace Ort
{
template<>
struct TypeToTensorType<half> { static constexpr ONNXTensorElementDataType type = ONNX_TENSOR_ELEMENT_DATA_TYPE_FLOAT16; };
}
#endif
template<typename T>
char* BlobFromImage(cv::Mat& iImg, T& iBlob) {
int channels = iImg.channels();
int imgHeight = iImg.rows;
int imgWidth = iImg.cols;
for (int c = 0; c < channels; c++)
{
for (int h = 0; h < imgHeight; h++)
{
for (int w = 0; w < imgWidth; w++)
{
iBlob[c * imgWidth * imgHeight + h * imgWidth + w] = typename std::remove_pointer<T>::type(
(iImg.at<cv::Vec3b>(h, w)[c]) / 255.0f);
}
}
}
return RET_OK;
}
char* YOLO_V8::PreProcess(cv::Mat& iImg, std::vector<int> iImgSize, cv::Mat& oImg)
{
if (iImg.channels() == 3)
{
oImg = iImg.clone();
cv::cvtColor(oImg, oImg, cv::COLOR_BGR2RGB);
}
else
{
cv::cvtColor(iImg, oImg, cv::COLOR_GRAY2RGB);
}
switch (modelType)
{
case YOLO_DETECT_V8:
case YOLO_POSE:
case YOLO_DETECT_V8_HALF:
case YOLO_POSE_V8_HALF://LetterBox
{
int new_h = iImgSize.at(0);
int new_w = iImgSize.at(1);
float r = min(new_w / (float)iImg.cols, new_h / (float)iImg.rows);
int resized_w = static_cast<int>(iImg.cols * r);
int resized_h = static_cast<int>(iImg.rows * r);
resizeScales = 1.0f / r;
cv::resize(oImg, oImg, cv::Size(resized_w, resized_h));
cv::Mat tempImg = cv::Mat::zeros(new_h, new_w, CV_8UC3);
oImg.copyTo(tempImg(cv::Rect(0, 0, resized_w, resized_h)));
oImg = tempImg;
break;
}
case YOLO_CLS://CenterCrop
{
int h = iImg.rows;
int w = iImg.cols;
int m = min(h, w);
int top = (h - m) / 2;
int left = (w - m) / 2;
cv::resize(oImg(cv::Rect(left, top, m, m)), oImg, cv::Size(iImgSize.at(1), iImgSize.at(0)));
break;
}
}
return RET_OK;
}
char* YOLO_V8::CreateSession(DL_INIT_PARAM& iParams) {
char* Ret = RET_OK;
std::regex pattern("[\u4e00-\u9fa5]");
bool result = std::regex_search(iParams.modelPath, pattern);
if (result)
{
Ret = "[YOLO_V8]:Your model path is error.Change your model path without chinese characters.";
std::cout << Ret << std::endl;
return Ret;
}
try
{
rectConfidenceThreshold = iParams.rectConfidenceThreshold;
iouThreshold = iParams.iouThreshold;
imgSize = iParams.imgSize;
modelType = iParams.modelType;
cudaEnable = iParams.cudaEnable;
env = Ort::Env(ORT_LOGGING_LEVEL_WARNING, "Yolo");
Ort::SessionOptions sessionOption;
if (iParams.cudaEnable)
{
OrtCUDAProviderOptions cudaOption;
cudaOption.device_id = 0;
sessionOption.AppendExecutionProvider_CUDA(cudaOption);
}
sessionOption.SetGraphOptimizationLevel(GraphOptimizationLevel::ORT_ENABLE_ALL);
sessionOption.SetIntraOpNumThreads(iParams.intraOpNumThreads);
sessionOption.SetLogSeverityLevel(iParams.logSeverityLevel);
#ifdef _WIN32
int ModelPathSize = MultiByteToWideChar(CP_UTF8, 0, iParams.modelPath.c_str(), static_cast<int>(iParams.modelPath.length()), nullptr, 0);
wchar_t* wide_cstr = new wchar_t[ModelPathSize + 1];
MultiByteToWideChar(CP_UTF8, 0, iParams.modelPath.c_str(), static_cast<int>(iParams.modelPath.length()), wide_cstr, ModelPathSize);
wide_cstr[ModelPathSize] = L'\0';
const wchar_t* modelPath = wide_cstr;
#else
const char* modelPath = iParams.modelPath.c_str();
#endif // _WIN32
session = new Ort::Session(env, modelPath, sessionOption);
Ort::AllocatorWithDefaultOptions allocator;
size_t inputNodesNum = session->GetInputCount();
for (size_t i = 0; i < inputNodesNum; i++)
{
Ort::AllocatedStringPtr input_node_name = session->GetInputNameAllocated(i, allocator);
char* temp_buf = new char[50];
strcpy(temp_buf, input_node_name.get());
inputNodeNames.push_back(temp_buf);
}
size_t OutputNodesNum = session->GetOutputCount();
for (size_t i = 0; i < OutputNodesNum; i++)
{
Ort::AllocatedStringPtr output_node_name = session->GetOutputNameAllocated(i, allocator);
char* temp_buf = new char[10];
strcpy(temp_buf, output_node_name.get());
outputNodeNames.push_back(temp_buf);
}
options = Ort::RunOptions{ nullptr };
WarmUpSession();
return RET_OK;
}
catch (const std::exception& e)
{
const char* str1 = "[YOLO_V8]:";
const char* str2 = e.what();
std::string result = std::string(str1) + std::string(str2);
char* merged = new char[result.length() + 1];
std::strcpy(merged, result.c_str());
std::cout << merged << std::endl;
delete[] merged;
return "[YOLO_V8]:Create session failed.";
}
}
char* YOLO_V8::RunSession(cv::Mat& iImg, std::vector<DL_RESULT>& oResult) {
#ifdef benchmark
clock_t starttime_1 = clock();
#endif // benchmark
char* Ret = RET_OK;
cv::Mat processedImg;
PreProcess(iImg, imgSize, processedImg);
if (modelType < 4)
{
float* blob = new float[processedImg.total() * 3];
BlobFromImage(processedImg, blob);
std::vector<int64_t> inputNodeDims = { 1, 3, imgSize.at(0), imgSize.at(1) };
TensorProcess(starttime_1, iImg, blob, inputNodeDims, oResult);
}
else
{
#ifdef USE_CUDA
half* blob = new half[processedImg.total() * 3];
BlobFromImage(processedImg, blob);
std::vector<int64_t> inputNodeDims = { 1,3,imgSize.at(0),imgSize.at(1) };
TensorProcess(starttime_1, iImg, blob, inputNodeDims, oResult);
#endif
}
return Ret;
}
template<typename N>
char* YOLO_V8::TensorProcess(clock_t& starttime_1, cv::Mat& iImg, N& blob, std::vector<int64_t>& inputNodeDims,
std::vector<DL_RESULT>& oResult) {
Ort::Value inputTensor = Ort::Value::CreateTensor<typename std::remove_pointer<N>::type>(
Ort::MemoryInfo::CreateCpu(OrtDeviceAllocator, OrtMemTypeCPU), blob, 3 * imgSize.at(0) * imgSize.at(1),
inputNodeDims.data(), inputNodeDims.size());
#ifdef benchmark
clock_t starttime_2 = clock();
#endif // benchmark
auto outputTensor = session->Run(options, inputNodeNames.data(), &inputTensor, 1, outputNodeNames.data(),
outputNodeNames.size());
#ifdef benchmark
clock_t starttime_3 = clock();
#endif // benchmark
Ort::TypeInfo typeInfo = outputTensor.front().GetTypeInfo();
auto tensor_info = typeInfo.GetTensorTypeAndShapeInfo();
std::vector<int64_t> outputNodeDims = tensor_info.GetShape();
auto output = outputTensor.front().GetTensorMutableData<typename std::remove_pointer<N>::type>();
delete[] blob;
switch (modelType)
{
case YOLO_DETECT_V8:
case YOLO_DETECT_V8_HALF:
{
int signalResultNum = outputNodeDims[1];//84
int strideNum = outputNodeDims[2];//8400
std::vector<int> class_ids;
std::vector<float> confidences;
std::vector<cv::Rect> boxes;
cv::Mat rawData;
if (modelType == YOLO_DETECT_V8)
{
// FP32
rawData = cv::Mat(signalResultNum, strideNum, CV_32F, output);
}
else
{
// FP16
rawData = cv::Mat(signalResultNum, strideNum, CV_16F, output);
rawData.convertTo(rawData, CV_32F);
}
// Note:
// ultralytics add transpose operator to the output of yolov8 model.which make yolov8/v5/v7 has same shape
// https://github.com/ultralytics/assets/releases/download/v8.4.0/yolov8n.pt
rawData = rawData.t();
float* data = (float*)rawData.data;
for (int i = 0; i < strideNum; ++i)
{
float* classesScores = data + 4;
cv::Mat scores(1, this->classes.size(), CV_32FC1, classesScores);
cv::Point class_id;
double maxClassScore;
cv::minMaxLoc(scores, 0, &maxClassScore, 0, &class_id);
if (maxClassScore > rectConfidenceThreshold)
{
confidences.push_back(maxClassScore);
class_ids.push_back(class_id.x);
float x = data[0];
float y = data[1];
float w = data[2];
float h = data[3];
int left = int((x - 0.5 * w) * resizeScales);
int top = int((y - 0.5 * h) * resizeScales);
int width = int(w * resizeScales);
int height = int(h * resizeScales);
boxes.push_back(cv::Rect(left, top, width, height));
}
data += signalResultNum;
}
std::vector<int> nmsResult;
cv::dnn::NMSBoxes(boxes, confidences, rectConfidenceThreshold, iouThreshold, nmsResult);
for (int i = 0; i < nmsResult.size(); ++i)
{
int idx = nmsResult[i];
DL_RESULT result;
result.classId = class_ids[idx];
result.confidence = confidences[idx];
result.box = boxes[idx];
oResult.push_back(result);
}
#ifdef benchmark
clock_t starttime_4 = clock();
double pre_process_time = (double)(starttime_2 - starttime_1) / CLOCKS_PER_SEC * 1000;
double process_time = (double)(starttime_3 - starttime_2) / CLOCKS_PER_SEC * 1000;
double post_process_time = (double)(starttime_4 - starttime_3) / CLOCKS_PER_SEC * 1000;
if (cudaEnable)
{
std::cout << "[YOLO_V8(CUDA)]: " << pre_process_time << "ms pre-process, " << process_time << "ms inference, " << post_process_time << "ms post-process." << std::endl;
}
else
{
std::cout << "[YOLO_V8(CPU)]: " << pre_process_time << "ms pre-process, " << process_time << "ms inference, " << post_process_time << "ms post-process." << std::endl;
}
#endif // benchmark
break;
}
case YOLO_CLS:
case YOLO_CLS_HALF:
{
cv::Mat rawData;
if (modelType == YOLO_CLS) {
// FP32
rawData = cv::Mat(1, this->classes.size(), CV_32F, output);
} else {
// FP16
rawData = cv::Mat(1, this->classes.size(), CV_16F, output);
rawData.convertTo(rawData, CV_32F);
}
float *data = (float *) rawData.data;
DL_RESULT result;
for (int i = 0; i < this->classes.size(); i++)
{
result.classId = i;
result.confidence = data[i];
oResult.push_back(result);
}
break;
}
default:
std::cout << "[YOLO_V8]: " << "Not support model type." << std::endl;
}
return RET_OK;
}
char* YOLO_V8::WarmUpSession() {
clock_t starttime_1 = clock();
cv::Mat iImg = cv::Mat(cv::Size(imgSize.at(1), imgSize.at(0)), CV_8UC3);
cv::Mat processedImg;
PreProcess(iImg, imgSize, processedImg);
if (modelType < 4)
{
float* blob = new float[iImg.total() * 3];
BlobFromImage(processedImg, blob);
std::vector<int64_t> YOLO_input_node_dims = { 1, 3, imgSize.at(0), imgSize.at(1) };
Ort::Value input_tensor = Ort::Value::CreateTensor<float>(
Ort::MemoryInfo::CreateCpu(OrtDeviceAllocator, OrtMemTypeCPU), blob, 3 * imgSize.at(0) * imgSize.at(1),
YOLO_input_node_dims.data(), YOLO_input_node_dims.size());
auto output_tensors = session->Run(options, inputNodeNames.data(), &input_tensor, 1, outputNodeNames.data(),
outputNodeNames.size());
delete[] blob;
clock_t starttime_4 = clock();
double post_process_time = (double)(starttime_4 - starttime_1) / CLOCKS_PER_SEC * 1000;
if (cudaEnable)
{
std::cout << "[YOLO_V8(CUDA)]: " << "Cuda warm-up cost " << post_process_time << " ms. " << std::endl;
}
}
else
{
#ifdef USE_CUDA
half* blob = new half[iImg.total() * 3];
BlobFromImage(processedImg, blob);
std::vector<int64_t> YOLO_input_node_dims = { 1,3,imgSize.at(0),imgSize.at(1) };
Ort::Value input_tensor = Ort::Value::CreateTensor<half>(Ort::MemoryInfo::CreateCpu(OrtDeviceAllocator, OrtMemTypeCPU), blob, 3 * imgSize.at(0) * imgSize.at(1), YOLO_input_node_dims.data(), YOLO_input_node_dims.size());
auto output_tensors = session->Run(options, inputNodeNames.data(), &input_tensor, 1, outputNodeNames.data(), outputNodeNames.size());
delete[] blob;
clock_t starttime_4 = clock();
double post_process_time = (double)(starttime_4 - starttime_1) / CLOCKS_PER_SEC * 1000;
if (cudaEnable)
{
std::cout << "[YOLO_V8(CUDA)]: " << "Cuda warm-up cost " << post_process_time << " ms. " << std::endl;
}
#endif
}
return RET_OK;
}

96
examples/YOLOv8-ONNXRuntime-CPP/inference.h Executable file
View File

@@ -0,0 +1,96 @@
// Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
#pragma once
#define RET_OK nullptr
#ifdef _WIN32
#include <Windows.h>
#include <direct.h>
#include <io.h>
#endif
#include <string>
#include <vector>
#include <cstdio>
#include <opencv2/opencv.hpp>
#include "onnxruntime_cxx_api.h"
#ifdef USE_CUDA
#include <cuda_fp16.h>
#endif
enum MODEL_TYPE
{
//FLOAT32 MODEL
YOLO_DETECT_V8 = 1,
YOLO_POSE = 2,
YOLO_CLS = 3,
//FLOAT16 MODEL
YOLO_DETECT_V8_HALF = 4,
YOLO_POSE_V8_HALF = 5,
YOLO_CLS_HALF = 6
};
typedef struct _DL_INIT_PARAM
{
std::string modelPath;
MODEL_TYPE modelType = YOLO_DETECT_V8;
std::vector<int> imgSize = { 640, 640 };
float rectConfidenceThreshold = 0.6;
float iouThreshold = 0.5;
int keyPointsNum = 2;//Note:kpt number for pose
bool cudaEnable = false;
int logSeverityLevel = 3;
int intraOpNumThreads = 1;
} DL_INIT_PARAM;
typedef struct _DL_RESULT
{
int classId;
float confidence;
cv::Rect box;
std::vector<cv::Point2f> keyPoints;
} DL_RESULT;
class YOLO_V8
{
public:
YOLO_V8();
~YOLO_V8();
public:
char* CreateSession(DL_INIT_PARAM& iParams);
char* RunSession(cv::Mat& iImg, std::vector<DL_RESULT>& oResult);
char* WarmUpSession();
template<typename N>
char* TensorProcess(clock_t& starttime_1, cv::Mat& iImg, N& blob, std::vector<int64_t>& inputNodeDims,
std::vector<DL_RESULT>& oResult);
char* PreProcess(cv::Mat& iImg, std::vector<int> iImgSize, cv::Mat& oImg);
std::vector<std::string> classes{};
private:
Ort::Env env;
Ort::Session* session;
bool cudaEnable;
Ort::RunOptions options;
std::vector<const char*> inputNodeNames;
std::vector<const char*> outputNodeNames;
MODEL_TYPE modelType;
std::vector<int> imgSize;
float rectConfidenceThreshold;
float iouThreshold;
float resizeScales;//letterbox scale
};

195
examples/YOLOv8-ONNXRuntime-CPP/main.cpp Executable file
View File

@@ -0,0 +1,195 @@
// Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
#include <iostream>
#include <iomanip>
#include "inference.h"
#include <filesystem>
#include <fstream>
#include <random>
void Detector(YOLO_V8*& p) {
std::filesystem::path current_path = std::filesystem::current_path();
std::filesystem::path imgs_path = current_path / "images";
for (auto& i : std::filesystem::directory_iterator(imgs_path))
{
if (i.path().extension() == ".jpg" || i.path().extension() == ".png" || i.path().extension() == ".jpeg")
{
std::string img_path = i.path().string();
cv::Mat img = cv::imread(img_path);
std::vector<DL_RESULT> res;
p->RunSession(img, res);
for (auto& re : res)
{
cv::RNG rng(cv::getTickCount());
cv::Scalar color(rng.uniform(0, 256), rng.uniform(0, 256), rng.uniform(0, 256));
cv::rectangle(img, re.box, color, 3);
float confidence = floor(100 * re.confidence) / 100;
std::cout << std::fixed << std::setprecision(2);
std::string label = p->classes[re.classId] + " " +
std::to_string(confidence).substr(0, std::to_string(confidence).size() - 4);
cv::rectangle(
img,
cv::Point(re.box.x, re.box.y - 25),
cv::Point(re.box.x + label.length() * 15, re.box.y),
color,
cv::FILLED
);
cv::putText(
img,
label,
cv::Point(re.box.x, re.box.y - 5),
cv::FONT_HERSHEY_SIMPLEX,
0.75,
cv::Scalar(0, 0, 0),
2
);
}
std::cout << "Press any key to exit" << std::endl;
cv::imshow("Result of Detection", img);
cv::waitKey(0);
cv::destroyAllWindows();
}
}
}
void Classifier(YOLO_V8*& p)
{
std::filesystem::path current_path = std::filesystem::current_path();
std::filesystem::path imgs_path = current_path;// / "images"
std::random_device rd;
std::mt19937 gen(rd());
std::uniform_int_distribution<int> dis(0, 255);
for (auto& i : std::filesystem::directory_iterator(imgs_path))
{
if (i.path().extension() == ".jpg" || i.path().extension() == ".png")
{
std::string img_path = i.path().string();
//std::cout << img_path << std::endl;
cv::Mat img = cv::imread(img_path);
std::vector<DL_RESULT> res;
char* ret = p->RunSession(img, res);
float positionY = 50;
for (int i = 0; i < res.size(); i++)
{
int r = dis(gen);
int g = dis(gen);
int b = dis(gen);
cv::putText(img, std::to_string(i) + ":", cv::Point(10, positionY), cv::FONT_HERSHEY_SIMPLEX, 1, cv::Scalar(b, g, r), 2);
cv::putText(img, std::to_string(res.at(i).confidence), cv::Point(70, positionY), cv::FONT_HERSHEY_SIMPLEX, 1, cv::Scalar(b, g, r), 2);
positionY += 50;
}
cv::imshow("TEST_CLS", img);
cv::waitKey(0);
cv::destroyAllWindows();
//cv::imwrite("E:\\output\\" + std::to_string(k) + ".png", img);
}
}
}
int ReadCocoYaml(YOLO_V8*& p) {
// Open the YAML file
std::ifstream file("coco.yaml");
if (!file.is_open())
{
std::cerr << "Failed to open file" << std::endl;
return 1;
}
// Read the file line by line
std::string line;
std::vector<std::string> lines;
while (std::getline(file, line))
{
lines.push_back(line);
}
// Find the start and end of the names section
std::size_t start = 0;
std::size_t end = 0;
for (std::size_t i = 0; i < lines.size(); i++)
{
if (lines[i].find("names:") != std::string::npos)
{
start = i + 1;
}
else if (start > 0 && lines[i].find(':') == std::string::npos)
{
end = i;
break;
}
}
// Extract the names
std::vector<std::string> names;
for (std::size_t i = start; i < end; i++)
{
std::stringstream ss(lines[i]);
std::string name;
std::getline(ss, name, ':'); // Extract the number before the delimiter
std::getline(ss, name); // Extract the string after the delimiter
names.push_back(name);
}
p->classes = names;
return 0;
}
void DetectTest()
{
YOLO_V8* yoloDetector = new YOLO_V8;
ReadCocoYaml(yoloDetector);
DL_INIT_PARAM params;
params.rectConfidenceThreshold = 0.1;
params.iouThreshold = 0.5;
params.modelPath = "yolov8n.onnx";
params.imgSize = { 640, 640 };
#ifdef USE_CUDA
params.cudaEnable = true;
// GPU FP32 inference
params.modelType = YOLO_DETECT_V8;
// GPU FP16 inference
//Note: change fp16 onnx model
//params.modelType = YOLO_DETECT_V8_HALF;
#else
// CPU inference
params.modelType = YOLO_DETECT_V8;
params.cudaEnable = false;
#endif
yoloDetector->CreateSession(params);
Detector(yoloDetector);
}
void ClsTest()
{
YOLO_V8* yoloDetector = new YOLO_V8;
std::string model_path = "cls.onnx";
ReadCocoYaml(yoloDetector);
DL_INIT_PARAM params{ model_path, YOLO_CLS, {224, 224} };
yoloDetector->CreateSession(params);
Classifier(yoloDetector);
}
int main()
{
//DetectTest();
ClsTest();
}