master

分支 (1)

管理

管理

master

yolov5_sort_cpp
/
yolov5_helmet.cpp

// #include <iostream>
// #include <chrono>
// #include <cmath>
// #include "cuda_utils.h"
// #include "logging.h"
// #include "common.hpp"
// #include "utils.h"
// #include "calibrator.h"
// #include <string>

// using namespace std;
// // using namespace cv;

// #define USE_FP16  // set USE_INT8 or USE_FP16 or USE_FP32
// #define DEVICE 0  // GPU id
// #define NMS_THRESH 0.4
// #define CONF_THRESH 0.5
// #define BATCH_SIZE 1

// // stuff we know about the network and the input/output blobs
// static const int INPUT_H = Yolo::INPUT_H;
// static const int INPUT_W = Yolo::INPUT_W;
// static const int CLASS_NUM = Yolo::CLASS_NUM;
// static const int OUTPUT_SIZE = Yolo::MAX_OUTPUT_BBOX_COUNT * sizeof(Yolo::Detection) / sizeof(float) + 1;  // we assume the yololayer outputs no more than MAX_OUTPUT_BBOX_COUNT boxes that conf >= 0.1
// const char* INPUT_BLOB_NAME = "data";
// const char* OUTPUT_BLOB_NAME = "prob";
// static Logger gLogger;

// static int get_width(int x, float gw, int divisor = 8) {
//     return int(ceil((x * gw) / divisor)) * divisor;
// }

// static int get_depth(int x, float gd) {
//     if (x == 1) return 1;
//     int r = round(x * gd);
//     if (x * gd - int(x * gd) == 0.5 && (int(x * gd) % 2) == 0) {
//         --r;
//     }
//     return std::max<int>(r, 1);
// }

// ICudaEngine* build_engine(unsigned int maxBatchSize, IBuilder* builder, IBuilderConfig* config, DataType dt, float& gd, float& gw, std::string& wts_name) {
//     INetworkDefinition* network = builder->createNetworkV2(0U);

//     // Create input tensor of shape {3, INPUT_H, INPUT_W} with name INPUT_BLOB_NAME
//     ITensor* data = network->addInput(INPUT_BLOB_NAME, dt, Dims3{ 3, INPUT_H, INPUT_W });
//     assert(data);

//     std::map<std::string, Weights> weightMap = loadWeights(wts_name);

//     /* ------ yolov5 backbone------ */
//     auto focus0 = focus(network, weightMap, *data, 3, get_width(64, gw), 3, "model.0");
//     auto conv1 = convBlock(network, weightMap, *focus0->getOutput(0), get_width(128, gw), 3, 2, 1, "model.1");
//     auto bottleneck_CSP2 = C3(network, weightMap, *conv1->getOutput(0), get_width(128, gw), get_width(128, gw), get_depth(3, gd), true, 1, 0.5, "model.2");
//     auto conv3 = convBlock(network, weightMap, *bottleneck_CSP2->getOutput(0), get_width(256, gw), 3, 2, 1, "model.3");
//     auto bottleneck_csp4 = C3(network, weightMap, *conv3->getOutput(0), get_width(256, gw), get_width(256, gw), get_depth(9, gd), true, 1, 0.5, "model.4");
//     auto conv5 = convBlock(network, weightMap, *bottleneck_csp4->getOutput(0), get_width(512, gw), 3, 2, 1, "model.5");
//     auto bottleneck_csp6 = C3(network, weightMap, *conv5->getOutput(0), get_width(512, gw), get_width(512, gw), get_depth(9, gd), true, 1, 0.5, "model.6");
//     auto conv7 = convBlock(network, weightMap, *bottleneck_csp6->getOutput(0), get_width(1024, gw), 3, 2, 1, "model.7");
//     auto spp8 = SPP(network, weightMap, *conv7->getOutput(0), get_width(1024, gw), get_width(1024, gw), 5, 9, 13, "model.8");

//     /* ------ yolov5 head ------ */
//     auto bottleneck_csp9 = C3(network, weightMap, *spp8->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.9");
//     auto conv10 = convBlock(network, weightMap, *bottleneck_csp9->getOutput(0), get_width(512, gw), 1, 1, 1, "model.10");

//     auto upsample11 = network->addResize(*conv10->getOutput(0));
//     assert(upsample11);
//     upsample11->setResizeMode(ResizeMode::kNEAREST);
//     upsample11->setOutputDimensions(bottleneck_csp6->getOutput(0)->getDimensions());

//     ITensor* inputTensors12[] = { upsample11->getOutput(0), bottleneck_csp6->getOutput(0) };
//     auto cat12 = network->addConcatenation(inputTensors12, 2);
//     auto bottleneck_csp13 = C3(network, weightMap, *cat12->getOutput(0), get_width(1024, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.13");
//     auto conv14 = convBlock(network, weightMap, *bottleneck_csp13->getOutput(0), get_width(256, gw), 1, 1, 1, "model.14");

//     auto upsample15 = network->addResize(*conv14->getOutput(0));
//     assert(upsample15);
//     upsample15->setResizeMode(ResizeMode::kNEAREST);
//     upsample15->setOutputDimensions(bottleneck_csp4->getOutput(0)->getDimensions());

//     ITensor* inputTensors16[] = { upsample15->getOutput(0), bottleneck_csp4->getOutput(0) };
//     auto cat16 = network->addConcatenation(inputTensors16, 2);

//     auto bottleneck_csp17 = C3(network, weightMap, *cat16->getOutput(0), get_width(512, gw), get_width(256, gw), get_depth(3, gd), false, 1, 0.5, "model.17");

//     /* ------ detect ------ */
//     IConvolutionLayer* det0 = network->addConvolutionNd(*bottleneck_csp17->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.24.m.0.weight"], weightMap["model.24.m.0.bias"]);
//     auto conv18 = convBlock(network, weightMap, *bottleneck_csp17->getOutput(0), get_width(256, gw), 3, 2, 1, "model.18");
//     ITensor* inputTensors19[] = { conv18->getOutput(0), conv14->getOutput(0) };
//     auto cat19 = network->addConcatenation(inputTensors19, 2);
//     auto bottleneck_csp20 = C3(network, weightMap, *cat19->getOutput(0), get_width(512, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.20");
//     IConvolutionLayer* det1 = network->addConvolutionNd(*bottleneck_csp20->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.24.m.1.weight"], weightMap["model.24.m.1.bias"]);
//     auto conv21 = convBlock(network, weightMap, *bottleneck_csp20->getOutput(0), get_width(512, gw), 3, 2, 1, "model.21");
//     ITensor* inputTensors22[] = { conv21->getOutput(0), conv10->getOutput(0) };
//     auto cat22 = network->addConcatenation(inputTensors22, 2);
//     auto bottleneck_csp23 = C3(network, weightMap, *cat22->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.23");
//     IConvolutionLayer* det2 = network->addConvolutionNd(*bottleneck_csp23->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.24.m.2.weight"], weightMap["model.24.m.2.bias"]);

//     auto yolo = addYoLoLayer(network, weightMap, "model.24", std::vector<IConvolutionLayer*>{det0, det1, det2});
//     yolo->getOutput(0)->setName(OUTPUT_BLOB_NAME);
//     network->markOutput(*yolo->getOutput(0));

//     // Build engine
//     builder->setMaxBatchSize(maxBatchSize);
//     config->setMaxWorkspaceSize(16 * (1 << 20));  // 16MB
// #if defined(USE_FP16)
//     config->setFlag(BuilderFlag::kFP16);
// #elif defined(USE_INT8)
//     std::cout << "Your platform support int8: " << (builder->platformHasFastInt8() ? "true" : "false") << std::endl;
//     assert(builder->platformHasFastInt8());
//     config->setFlag(BuilderFlag::kINT8);
//     Int8EntropyCalibrator2* calibrator = new Int8EntropyCalibrator2(1, INPUT_W, INPUT_H, "./coco_calib/", "int8calib.table", INPUT_BLOB_NAME);
//     config->setInt8Calibrator(calibrator);
// #endif

//     std::cout << "Building engine, please wait for a while..." << std::endl;
//     ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config);
//     std::cout << "Build engine successfully!" << std::endl;

//     // Don't need the network any more
//     network->destroy();

//     // Release host memory
//     for (auto& mem : weightMap)
//     {
//         free((void*)(mem.second.values));
//     }

//     return engine;
// }

// ICudaEngine* build_engine_p6(unsigned int maxBatchSize, IBuilder* builder, IBuilderConfig* config, DataType dt, float& gd, float& gw, std::string& wts_name) {
//     INetworkDefinition* network = builder->createNetworkV2(0U);

//     // Create input tensor of shape {3, INPUT_H, INPUT_W} with name INPUT_BLOB_NAME
//     ITensor* data = network->addInput(INPUT_BLOB_NAME, dt, Dims3{ 3, INPUT_H, INPUT_W });
//     assert(data);

//     std::map<std::string, Weights> weightMap = loadWeights(wts_name);

//     /* ------ yolov5 backbone------ */
//     auto focus0 = focus(network, weightMap, *data, 3, get_width(64, gw), 3, "model.0");
//     auto conv1 = convBlock(network, weightMap, *focus0->getOutput(0), get_width(128, gw), 3, 2, 1, "model.1");
//     auto c3_2 = C3(network, weightMap, *conv1->getOutput(0), get_width(128, gw), get_width(128, gw), get_depth(3, gd), true, 1, 0.5, "model.2");
//     auto conv3 = convBlock(network, weightMap, *c3_2->getOutput(0), get_width(256, gw), 3, 2, 1, "model.3");
//     auto c3_4 = C3(network, weightMap, *conv3->getOutput(0), get_width(256, gw), get_width(256, gw), get_depth(9, gd), true, 1, 0.5, "model.4");
//     auto conv5 = convBlock(network, weightMap, *c3_4->getOutput(0), get_width(512, gw), 3, 2, 1, "model.5");
//     auto c3_6 = C3(network, weightMap, *conv5->getOutput(0), get_width(512, gw), get_width(512, gw), get_depth(9, gd), true, 1, 0.5, "model.6");
//     auto conv7 = convBlock(network, weightMap, *c3_6->getOutput(0), get_width(768, gw), 3, 2, 1, "model.7");
//     auto c3_8 = C3(network, weightMap, *conv7->getOutput(0), get_width(768, gw), get_width(768, gw), get_depth(3, gd), true, 1, 0.5, "model.8");
//     auto conv9 = convBlock(network, weightMap, *c3_8->getOutput(0), get_width(1024, gw), 3, 2, 1, "model.9");
//     auto spp10 = SPP(network, weightMap, *conv9->getOutput(0), get_width(1024, gw), get_width(1024, gw), 3, 5, 7, "model.10");
//     auto c3_11 = C3(network, weightMap, *spp10->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.11");

//     /* ------ yolov5 head ------ */
//     auto conv12 = convBlock(network, weightMap, *c3_11->getOutput(0), get_width(768, gw), 1, 1, 1, "model.12");
//     auto upsample13 = network->addResize(*conv12->getOutput(0));
//     assert(upsample13);
//     upsample13->setResizeMode(ResizeMode::kNEAREST);
//     upsample13->setOutputDimensions(c3_8->getOutput(0)->getDimensions());
//     ITensor* inputTensors14[] = { upsample13->getOutput(0), c3_8->getOutput(0) };
//     auto cat14 = network->addConcatenation(inputTensors14, 2);
//     auto c3_15 = C3(network, weightMap, *cat14->getOutput(0), get_width(1536, gw), get_width(768, gw), get_depth(3, gd), false, 1, 0.5, "model.15");

//     auto conv16 = convBlock(network, weightMap, *c3_15->getOutput(0), get_width(512, gw), 1, 1, 1, "model.16");
//     auto upsample17 = network->addResize(*conv16->getOutput(0));
//     assert(upsample17);
//     upsample17->setResizeMode(ResizeMode::kNEAREST);
//     upsample17->setOutputDimensions(c3_6->getOutput(0)->getDimensions());
//     ITensor* inputTensors18[] = { upsample17->getOutput(0), c3_6->getOutput(0) };
//     auto cat18 = network->addConcatenation(inputTensors18, 2);
//     auto c3_19 = C3(network, weightMap, *cat18->getOutput(0), get_width(1024, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.19");

//     auto conv20 = convBlock(network, weightMap, *c3_19->getOutput(0), get_width(256, gw), 1, 1, 1, "model.20");
//     auto upsample21 = network->addResize(*conv20->getOutput(0));
//     assert(upsample21);
//     upsample21->setResizeMode(ResizeMode::kNEAREST);
//     upsample21->setOutputDimensions(c3_4->getOutput(0)->getDimensions());
//     ITensor* inputTensors21[] = { upsample21->getOutput(0), c3_4->getOutput(0) };
//     auto cat22 = network->addConcatenation(inputTensors21, 2);
//     auto c3_23 = C3(network, weightMap, *cat22->getOutput(0), get_width(512, gw), get_width(256, gw), get_depth(3, gd), false, 1, 0.5, "model.23");

//     auto conv24 = convBlock(network, weightMap, *c3_23->getOutput(0), get_width(256, gw), 3, 2, 1, "model.24");
//     ITensor* inputTensors25[] = { conv24->getOutput(0), conv20->getOutput(0) };
//     auto cat25 = network->addConcatenation(inputTensors25, 2);
//     auto c3_26 = C3(network, weightMap, *cat25->getOutput(0), get_width(1024, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.26");

//     auto conv27 = convBlock(network, weightMap, *c3_26->getOutput(0), get_width(512, gw), 3, 2, 1, "model.27");
//     ITensor* inputTensors28[] = { conv27->getOutput(0), conv16->getOutput(0) };
//     auto cat28 = network->addConcatenation(inputTensors28, 2);
//     auto c3_29 = C3(network, weightMap, *cat28->getOutput(0), get_width(1536, gw), get_width(768, gw), get_depth(3, gd), false, 1, 0.5, "model.29");

//     auto conv30 = convBlock(network, weightMap, *c3_29->getOutput(0), get_width(768, gw), 3, 2, 1, "model.30");
//     ITensor* inputTensors31[] = { conv30->getOutput(0), conv12->getOutput(0) };
//     auto cat31 = network->addConcatenation(inputTensors31, 2);
//     auto c3_32 = C3(network, weightMap, *cat31->getOutput(0), get_width(2048, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.32");

//     /* ------ detect ------ */
//     IConvolutionLayer* det0 = network->addConvolutionNd(*c3_23->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.33.m.0.weight"], weightMap["model.33.m.0.bias"]);
//     IConvolutionLayer* det1 = network->addConvolutionNd(*c3_26->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.33.m.1.weight"], weightMap["model.33.m.1.bias"]);
//     IConvolutionLayer* det2 = network->addConvolutionNd(*c3_29->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.33.m.2.weight"], weightMap["model.33.m.2.bias"]);
//     IConvolutionLayer* det3 = network->addConvolutionNd(*c3_32->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.33.m.3.weight"], weightMap["model.33.m.3.bias"]);

//     auto yolo = addYoLoLayer(network, weightMap, "model.33", std::vector<IConvolutionLayer*>{det0, det1, det2, det3});
//     yolo->getOutput(0)->setName(OUTPUT_BLOB_NAME);
//     network->markOutput(*yolo->getOutput(0));

//     // Build engine
//     builder->setMaxBatchSize(maxBatchSize);
//     config->setMaxWorkspaceSize(16 * (1 << 20));  // 16MB
// #if defined(USE_FP16)
//     config->setFlag(BuilderFlag::kFP16);
// #elif defined(USE_INT8)
//     std::cout << "Your platform support int8: " << (builder->platformHasFastInt8() ? "true" : "false") << std::endl;
//     assert(builder->platformHasFastInt8());
//     config->setFlag(BuilderFlag::kINT8);
//     Int8EntropyCalibrator2* calibrator = new Int8EntropyCalibrator2(1, INPUT_W, INPUT_H, "./coco_calib/", "int8calib.table", INPUT_BLOB_NAME);
//     config->setInt8Calibrator(calibrator);
// #endif

//     std::cout << "Building engine, please wait for a while..." << std::endl;
//     ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config);
//     std::cout << "Build engine successfully!" << std::endl;

//     // Don't need the network any more
//     network->destroy();

//     // Release host memory
//     for (auto& mem : weightMap)
//     {
//         free((void*)(mem.second.values));
//     }

//     return engine;
// }

// void APIToModel(unsigned int maxBatchSize, IHostMemory** modelStream, bool& is_p6, float& gd, float& gw, std::string& wts_name) {
//     // Create builder
//     IBuilder* builder = createInferBuilder(gLogger);
//     IBuilderConfig* config = builder->createBuilderConfig();

//     // Create model to populate the network, then set the outputs and create an engine
//     ICudaEngine *engine = nullptr;
//     if (is_p6) {
//         engine = build_engine_p6(maxBatchSize, builder, config, DataType::kFLOAT, gd, gw, wts_name);
//     } else {
//         engine = build_engine(maxBatchSize, builder, config, DataType::kFLOAT, gd, gw, wts_name);
//     }
//     assert(engine != nullptr);

//     // Serialize the engine
//     (*modelStream) = engine->serialize();

//     // Close everything down
//     engine->destroy();
//     builder->destroy();
//     config->destroy();
// }

// void doInference(IExecutionContext& context, cudaStream_t& stream, void **buffers, float* input, float* output, int batchSize) {
//     // DMA input batch data to device, infer on the batch asynchronously, and DMA output back to host
//     CUDA_CHECK(cudaMemcpyAsync(buffers[0], input, batchSize * 3 * INPUT_H * INPUT_W * sizeof(float), cudaMemcpyHostToDevice, stream));
//     context.enqueue(batchSize, buffers, stream, nullptr);
//     CUDA_CHECK(cudaMemcpyAsync(output, buffers[1], batchSize * OUTPUT_SIZE * sizeof(float), cudaMemcpyDeviceToHost, stream));
//     cudaStreamSynchronize(stream);
// }

// bool parse_args(int argc, char** argv, std::string& engine, int& usb) {
//     if(argc<4)
//         return false;
//     if (std::string(argv[1]) == "-d" && argc == 4) {
//         engine = std::string(argv[2]);
//         usb = atoi(argv[3]);
//     } else {
//         return false;
//     }
//     return true;
// }

// cv::Mat show_fps(cv::Mat img, float fps){
//     // string fps_s = to_string(fps).substr(0, 5);
//     char text_s[10];
//     sprintf(text_s, "%.2f", fps);
//     string fps_s = text_s;
//     fps_s = "FPS: " + fps_s;
//     putText(img, fps_s, cv::Point(20,20), cv::FONT_HERSHEY_COMPLEX, 0.5, cv::Scalar(0, 255, 255), 1);
//     return img;
// }

// vector<string> get_categories(){
//     vector<string> categories = {"person", "head", "helmet"};
//     return categories;
// }

// vector<cv::Scalar> gen_colors(int num_colors){
//     vector<int> bgrs;
//     if(num_colors<=27)
//         bgrs = {0, 125, 255};
//     else if(num_colors<=125)
//         bgrs= {0, 64, 128, 178, 255};
//     else
//         cout<<"num_classes > 125"<<endl;
//     assert(num_colors<=125);
//     vector<cv::Scalar> all_colors;
//     cv::Scalar color;
//     for(int b=0; b<bgrs.size(); b++)
//         for(int g=0; g<bgrs.size(); g++)
//             for(int r=0; r<bgrs.size(); r++){
//                 color = cv::Scalar(bgrs.at(b), bgrs.at(g), bgrs.at(r));
//                 all_colors.push_back(color);
//             }
//     //    std::srand(unsigned(time(0)));
//     // default setting seed
//     random_shuffle(all_colors.begin(), all_colors.end());
//     vector<cv::Scalar> colors;
//     for(int i=0; i<num_colors; i++)
//         colors.push_back(all_colors[i]);
//     return colors;
// }

// // ./yolov5_cym -d /home/cym/CYM/models/yolov5_helmet/yolov5m-4.0.engine usb
// int main(int argc, char** argv) {

//     cudaSetDevice(DEVICE);

//     std::string wts_name = "";
//     std::string engine_name = "";
//     int usb = 0;
//     if (!parse_args(argc, argv, engine_name, usb)) {
//         std::cerr << "arguments not right!" << std::endl;
//         std::cerr << "./yolov5 -d [string(engine)] [int(usb)] // deserialize plan file and run inference" << std::endl;
//         return -1;
//     }

//     // deserialize the .engine and run inference
//     std::ifstream file(engine_name, std::ios::binary);
//     if (!file.good()) {
//         std::cerr << "read " << engine_name << " error!" << std::endl;
//         return -1;
//     }
//     char *trtModelStream = nullptr;
//     size_t size = 0;
//     file.seekg(0, file.end);
//     size = file.tellg();
//     file.seekg(0, file.beg);
//     trtModelStream = new char[size];
//     assert(trtModelStream);
//     file.read(trtModelStream, size);
//     file.close();

//     // prepare input data ---------------------------
//     static float data[BATCH_SIZE * 3 * INPUT_H * INPUT_W];
//     //for (int i = 0; i < 3 * INPUT_H * INPUT_W; i++)
//     //    data[i] = 1.0;
//     static float prob[BATCH_SIZE * OUTPUT_SIZE];
//     IRuntime* runtime = createInferRuntime(gLogger);
//     assert(runtime != nullptr);
//     ICudaEngine* engine = runtime->deserializeCudaEngine(trtModelStream, size);
//     assert(engine != nullptr);
//     IExecutionContext* context = engine->createExecutionContext();
//     assert(context != nullptr);
//     delete[] trtModelStream;
//     assert(engine->getNbBindings() == 2);
//     void* buffers[2];
//     // In order to bind the buffers, we need to know the names of the input and output tensors.
//     // Note that indices are guaranteed to be less than IEngine::getNbBindings()
//     const int inputIndex = engine->getBindingIndex(INPUT_BLOB_NAME);
//     const int outputIndex = engine->getBindingIndex(OUTPUT_BLOB_NAME);
//     assert(inputIndex == 0);
//     assert(outputIndex == 1);
//     // Create GPU buffers on device
//     CUDA_CHECK(cudaMalloc(&buffers[inputIndex], BATCH_SIZE * 3 * INPUT_H * INPUT_W * sizeof(float)));
//     CUDA_CHECK(cudaMalloc(&buffers[outputIndex], BATCH_SIZE * OUTPUT_SIZE * sizeof(float)));
//     // Create stream
//     cudaStream_t stream;
//     CUDA_CHECK(cudaStreamCreate(&stream));

//     vector<string> categories = get_categories();
//     vector<cv::Scalar>colors = gen_colors(categories.size());
//     std::vector<int> target_cls_id = {1,  2};

//     int frame_count = 0;
//     cv::VideoCapture capture;
//     capture.open(usb);
//     if(!capture.isOpened()){
//         printf("could not load video data...\n");
//         return -1;
//     }
//     float fps = 0.0;
//     auto fps_start = std::chrono::system_clock::now();
//     while(true) {
//         frame_count++;
//         cv::Mat img;
//         capture >> img;
//         if (img.empty()){ printf("Could not capture images\n"); break; }
//         cv::Mat pr_img = preprocess_img(img, INPUT_W, INPUT_H); // letterbox BGR to RGB
//         int i = 0;
//         for (int row = 0; row < INPUT_H; ++row) {
//             uchar* uc_pixel = pr_img.data + row * pr_img.step;
//             for (int col = 0; col < INPUT_W; ++col) {
//                 data[i] = (float)uc_pixel[2] / 255.0;
//                 data[i + INPUT_H * INPUT_W] = (float)uc_pixel[1] / 255.0;
//                 data[i + 2 * INPUT_H * INPUT_W] = (float)uc_pixel[0] / 255.0;
//                 uc_pixel += 3; ++i;
//             }
//         }
//         // Run inference
//         auto start = std::chrono::system_clock::now();
//         doInference(*context, stream, buffers, data, prob, BATCH_SIZE);
//         auto end = std::chrono::system_clock::now();
//         printf("Frame: %d. The inference time is: %dms. FPS:%.3f.\n", frame_count,  std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count(), fps);
//         // std::vector<Yolo::Detection> batch_res;
//         // nms(batch_res, &prob[0], CONF_THRESH, NMS_THRESH);

//         std::vector<float> merge_cls_id = {1,2};
//         std::vector<Yolo::Detection> batch_res;
//         nms_merge_cls_id(batch_res, &prob[0], merge_cls_id, CONF_THRESH, NMS_THRESH);

//         // // merge_cls_id: head and helmet共同做nms.
//         // std::vector<Yolo::Detection> res;
//         // nms(res, &prob[0], CONF_THRESH, NMS_THRESH);
//         // std::vector<Yolo::Detection> batch_res;
//         // std::vector<float> merge_cls_id = {1,2};
//         // nms_merge(batch_res, res, merge_cls_id, CONF_THRESH, NMS_THRESH);

//         // draw bounding box
//         for (size_t j = 0; j < batch_res.size(); j++) {
//             cv::Rect r = get_rect(img, batch_res[j].bbox);
//             int class_id = (int)batch_res[j].class_id;
//             if(std::find(target_cls_id.begin(), target_cls_id.end(), class_id) != target_cls_id.end()){
//                 cv::rectangle(img, r, colors[class_id], 2);
//                 char text[10]; sprintf(text, "%.2f", batch_res[j].conf);
//                 string text_s = text; text_s = categories[class_id] + ": "+text_s;
//                 cv::putText(img, text_s, cv::Point(r.x, r.y - 1), cv::FONT_HERSHEY_PLAIN, 1.2, cv::Scalar(0xFF, 0xFF, 0xFF), 2);
//             }
//         }
//         auto fps_end = std::chrono::system_clock::now();
//         float all_time = std::chrono::duration_cast<std::chrono::milliseconds>(fps_end - fps_start).count();
//         float curr_fps = 1000.0/all_time;
//         if(fps==0.0) fps = curr_fps; else fps = fps*0.95 + curr_fps*0.05;

//         fps_start = fps_end;
//         img = show_fps(img, fps);
//         cv::imshow("video", img);
//         int key = cv::waitKey(1);
//         if(key==27)
//             break;
//     }
//     // Release stream and buffers
//     cudaStreamDestroy(stream);
//     CUDA_CHECK(cudaFree(buffers[inputIndex]));
//     CUDA_CHECK(cudaFree(buffers[outputIndex]));
//     // Destroy the engine
//     context->destroy();
//     engine->destroy();
//     runtime->destroy();

//     return 0;
// }