OpenVINO2024C++推理使用技巧合集

#include 

ov::Core ie;ov::CompiledModel compiled_model = ie.compile_model(settings.getWeight_file(), "CPU");infer_request = compiled_model.create_infer_request();

ov::Core ie;auto model = ie.read_model(settings.getWeight_file());auto inputs = model->inputs();
// change the input as dynamic shape supportfor(auto input_one : inputs){         auto input_shape = input_one.get_partial_shape();         input_shape[0] = 1;         input_shape[1] = 3;         input_shape[2] = -1;         input_shape[3] = -1;}
ov::CompiledModel compiled_model = ie.compile_model(model, "CPU");infer_request = compiled_model.create_infer_request();

ov::Core ie;std::cout<<"model file: "<std::endl;< span="">auto model = ie.read_model(settings.getWeight_file());std::cout<<"read model file finished!"<<std::endl;< span="">
// setting input data format and layoutov::preprocess::PrePostProcessor ppp(model);ov::preprocess::InputInfo& inputInfo0 = ppp.input(0);inputInfo0.tensor().set_element_type(ov::element::u8);inputInfo0.tensor().set_layout({ "NCHW" });inputInfo0.model().set_layout("NCHW");
ov::preprocess::InputInfo& inputInfo1 = ppp.input(1);inputInfo1.tensor().set_element_type(ov::element::u8);inputInfo1.tensor().set_layout({ "NCHW" });inputInfo1.model().set_layout("NCHW");model = ppp.build();
ov::CompiledModel compiled_model = ie.compile_model(model, "CPU");this->infer_request = compiled_model.create_infer_request();

ov_model = ov.convert_model("D:/python/my_yolov8_train_demo/yolov8n.onnx",                             input=[[1, 3, 640, 640]])ov.save_model(ov_model, str("D:/bird_test/back1/yolov8_ov.xml"))

ov::preprocess::PrePostProcessor ppp(model);ov::preprocess::InputInfo& input = ppp.input(tensor_name);// we only need to know where is C dimensioninput.model().set_layout("...C");// specify scale and mean values, order of operations is importantinput.preprocess().mean(116.78f).scale({ 57.21f, 57.45f, 57.73f });// insert preprocessing operations to the 'model'model = ppp.build();

// 预处理cv::Mat blob_image;resize(image, blob_image, cv::Size(input_w, input_h));blob_image.convertTo(blob_image, CV_32F);blob_image = blob_image / 255.0;

cv::Mat blob = cv::dnn::blobFromImage(image, 1 / 255.0, cv::Size(640, 640), cv::Scalar(0, 0, 0), true, false);

this->infer_request.infer();

auto restart_once = true;infer_request.set_callback([&, restart_once](std::exception_ptr exception_ptr) mutable {    if (exception_ptr) {        // procces exception or rethrow it.        std::rethrow_exception(exception_ptr);    } else {        // Extract inference result        ov::Tensor output_tensor = infer_request.get_output_tensor();        // Restart inference if needed        if (restart_once) {            infer_request.start_async();            restart_once = false;        }    }});// Start inference without blocking current threadinfer_request.start_async();// Get inference status immediatelybool status = infer_request.wait_for(std::chrono::milliseconds{0});// Wait for one milisecondstatus = infer_request.wait_for(std::chrono::milliseconds{1});// Wait for inference completioninfer_request.wait();

bgr.convertTo(bgr, CV_32FC3);gray.convertTo(gray, CV_32F, 1.0/255);
ov::Tensor blob1(input_tensor_1.get_element_type(), input_tensor_1.get_shape(), (float *)bgr.data);ov::Tensor blob2(input_tensor_2.get_element_type(), input_tensor_2.get_shape(), (float *)gray.data);

const float* prob = (float*)output.data();const ov::Shape outputDims = output.get_shape();size_t numRows = outputDims[1];size_t numCols = outputDims[2];

cv::Mat detOut(numRows, numCols, CV_32F, (float*)prob);

cv::Mat detOut(numRows, numCols, CV_32FC3, (float*)prob);

cv::Mat detOut(numRows, numCols, CV_32F, (float*)prob);