#include <iostream>
#include <chrono>
#include <cmath>
#include "cuda_utils.h"
#include "logging.h"
#include "yolov5_common.h"
#include "utils.h"
#include "calibrator.h"
#include "preprocess.h"

/*
 *相关宏定义:
 *量化模式:TensorRT仅支持INT8,FP16,FP32三种量化,INT8量化较为复杂
 *GPU ID:默认是0
 *NMS阈值
 *置信度阈值
 *BATCH_SIZE
 *图像最大尺寸阈值
*/
#define USE_FP32  // 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
#define MAX_IMAGE_INPUT_SIZE_THRESH 3000 * 3000 // ensure it exceed the maximum size in the input images !

//输入高度,输入宽度,类别,输出大小,在yololayer.h里面可以配置,默认宽高都为640,类别为80
// 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";  //指定输入输出blob，和资源文件夹
const char* OUTPUT_BLOB_NAME = "prob";
static Logger gLogger;      //tensorrt logger为TensorRT API中各方法的必须参数

//要想用TensorRT执行推理,首先需要ICudaEngine对象创建引擎engine,然后利用IExecutionContext接口执行推理
//获取宽度
static int get_width(int x, float gw, int divisor = 8) {
    return int(ceil((x * gw) / divisor)) * divisor;
}

//获取深度
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);
}

//构建普通引擎(例:yolov5s,yolov5m...)
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 conv0 = convBlock(network, weightMap, *data,  get_width(64, gw), 6, 2, 1,  "model.0");
    assert(conv0);
    auto conv1 = convBlock(network, weightMap, *conv0->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(6, 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 bottleneck_csp8 = C3(network, weightMap, *conv7->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), true, 1, 0.5, "model.8");
    auto spp9 = SPPF(network, weightMap, *bottleneck_csp8->getOutput(0), get_width(1024, gw), get_width(1024, gw), 5, "model.9");
    /* ------ yolov5 head ------ */
    auto conv10 = convBlock(network, weightMap, *spp9->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;
}

//构建p6引擎(例:yolov5s6,yolov5m6...)
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 conv0 = convBlock(network, weightMap, *data,  get_width(64, gw), 6, 2, 1,  "model.0");
    auto conv1 = convBlock(network, weightMap, *conv0->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(6, 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 c3_10 = C3(network, weightMap, *conv9->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), true, 1, 0.5, "model.10");
    auto sppf11 = SPPF(network, weightMap, *c3_10->getOutput(0), get_width(1024, gw), get_width(1024, gw), 5, "model.11");

    /* ------ yolov5 head ------ */
    auto conv12 = convBlock(network, weightMap, *sppf11->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;
}

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

    // 创建模型来填充网络，然后设置输出并创建一个引擎  
    // 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
    //序列化引擎生成模型流
    (*modelStream) = engine->serialize();

    // Close everything down
    //释放相关资源
    engine->destroy();
    builder->destroy();
    config->destroy();
}

//执行推理
void doInference(IExecutionContext& context, cudaStream_t& stream, void **buffers, float* output, int batchSize) {
    // infer on the batch asynchronously, and DMA output back to host
    context.enqueue(batchSize, buffers, stream, nullptr);   //执行异步推理(调用context->enqueueV2即可执行异步推理,如果用同步推理的话,可以调用context->executeV2)
    CUDA_CHECK(cudaMemcpyAsync(output, buffers[1], batchSize * OUTPUT_SIZE * sizeof(float), cudaMemcpyDeviceToHost, stream));   //把推理后的结果从GPU上拷贝到CPU上
    cudaStreamSynchronize(stream); //同步之前创建的cuda流，原因很简单，直接使用的context->enqueueV2函数是异步推理,因此需要把cuda流同步一下
}

//解析命令参数
bool parse_args(int argc, char** argv, std::string& wts, std::string& engine, bool& is_p6, float& gd, float& gw, std::string& img_dir) {
    if (argc < 4) return false;
    if (std::string(argv[1]) == "-s" && (argc == 5 || argc == 7)) {
        wts = std::string(argv[2]);
        engine = std::string(argv[3]);
        auto net = std::string(argv[4]);
        if (net[0] == 'n') {    //gw width_multiple系数 gd depth_multiple系数 depth_multiple控制网络的深度,width_multiple控制网络的宽度。
            gd = 0.33;
            gw = 0.25;
        } else if (net[0] == 's') {
            gd = 0.33;
            gw = 0.50;
        } else if (net[0] == 'm') {
            gd = 0.67;
            gw = 0.75;
        } else if (net[0] == 'l') {
            gd = 1.0;
            gw = 1.0;
        } else if (net[0] == 'x') {
            gd = 1.33;
            gw = 1.25;
        } else if (net[0] == 'c' && argc == 7) {
            gd = atof(argv[5]);
            gw = atof(argv[6]);
        } else {
            return false;
        }
        if (net.size() == 2 && net[1] == '6') {
            is_p6 = true;
        }
    } else if (std::string(argv[1]) == "-d" && argc == 4) {
        engine = std::string(argv[2]);
        img_dir = std::string(argv[3]);
    } else {
        return false;
    }
    return true;
}

int main(int argc, char** argv) {
    cudaSetDevice(DEVICE);  //设置GPU 

    std::string wts_name = "";  //wts及engine模型名称
    std::string engine_name = "";
    bool is_p6 = false; //默认不是P6模型
    float gd = 0.0f, gw = 0.0f;
    std::string img_dir;    //输入图像的路径

    //解析传入命令
    if (!parse_args(argc, argv, wts_name, engine_name, is_p6, gd, gw, img_dir)) {
        std::cerr << "arguments not right!" << std::endl;
        std::cerr << "./yolov5 -s [.wts] [.engine] [n/s/m/l/x/n6/s6/m6/l6/x6 or c/c6 gd gw]  // serialize model to plan file" << std::endl;
        std::cerr << "./yolov5 -d [.engine] ../../samples  // deserialize plan file and run inference" << std::endl;
        return -1;
    }

    // create a model using the API directly and serialize it to a stream
    //直接使用API创建一个模型，并将其序列化为流  
    if (!wts_name.empty()) {
        IHostMemory* modelStream{ nullptr };
        APIToModel(BATCH_SIZE, &modelStream, is_p6, gd, gw, wts_name);
        assert(modelStream != nullptr);
        std::ofstream p(engine_name, std::ios::binary);
        if (!p) {
            std::cerr << "could not open plan output file" << std::endl;
            return -1;
        }
        p.write(reinterpret_cast<const char*>(modelStream->data()), modelStream->size());
        modelStream->destroy();
        return 0;
    }

    // deserialize the .engine and run inference
    //反序列化模型并运行推理
    std::ifstream file(engine_name, std::ios::binary);
    if (!file.good()) {
        std::cerr << "read " << engine_name << " error!" << std::endl;
        return -1;
    }

    //创建tensorRT流对象trtModelStream,这个就跟文件流中的ifstream类似的
    //trtModelStream是一块内存区域,用于保存序列化的plan文件
    char *trtModelStream = nullptr;
    size_t size = 0;
    file.seekg(0, file.end);    //将指针移动至距离文件末尾0处的位置
    size = file.tellg();    //获得当前字符的位置
    file.seekg(0, file.beg);    //将指针移动至距离文件开头0处的位置
    trtModelStream = new char[size];
    assert(trtModelStream);
    file.read(trtModelStream, size);    //将序列化engine模型(数据及数据大小)读入trtModelStream
    file.close();

    std::vector<std::string> file_names;    //读取输入的图像数据
    if (read_files_in_dir(img_dir.c_str(), file_names) < 0) {
        std::cerr << "read_files_in_dir failed." << std::endl;
        return -1;
    }

    static float prob[BATCH_SIZE * OUTPUT_SIZE];    //输出的shape大小
    IRuntime* runtime = createInferRuntime(gLogger);     //创建运行时环境IRuntime对象,传入gLogger用于打印信息
    assert(runtime != nullptr);
    ICudaEngine* engine = runtime->deserializeCudaEngine(trtModelStream, size); //反序列化引擎engine(根据trtModelStream反序列化)
    assert(engine != nullptr);
    IExecutionContext* context = engine->createExecutionContext();  //创建上下文环境,主要用于inference函数中启动cuda核
    assert(context != nullptr);
    delete[] trtModelStream;    //析构trtModelStream
    assert(engine->getNbBindings() == 2);
    float* buffers[2];
    //为了绑定缓冲区，我们需要知道输入和输出张量的名称。  
    //注意索引保证小于IEngine:: gettnbbindings ()  
    //用TensorRT去推理模型，就必须要传入一个存有输入和输出数据（的指针）的缓冲区,
    //因此我们需要用engine->getBindingIndex这个函数去拿到输入和输出在网络中的位置。
    //具体的INPUT_NAME和OUTPUT_NAME是自己在生成序列化模型的时候设置的
    //如果是像类似TensorRTx那样的工程，从头到尾用TensorRT的API去实现一个模型
    //那么INPUT_NAME和OUTPUT_NAME就是在设置输入层和输出层自己设置的name。
    // 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
    //在设备端(GPU)申请内存
    CUDA_CHECK(cudaMalloc((void**)&buffers[inputIndex], BATCH_SIZE * 3 * INPUT_H * INPUT_W * sizeof(float)));
    CUDA_CHECK(cudaMalloc((void**)&buffers[outputIndex], BATCH_SIZE * OUTPUT_SIZE * sizeof(float)));

    // Create stream
    //创建一个cuda流,推理的时候需要用到
    cudaStream_t stream;
    CUDA_CHECK(cudaStreamCreate(&stream));
    uint8_t* img_host = nullptr;
    uint8_t* img_device = nullptr;
    // prepare input data cache in pinned memory 
    // 在HOST侧申请预处理数据缓存
    CUDA_CHECK(cudaMallocHost((void**)&img_host, MAX_IMAGE_INPUT_SIZE_THRESH * 3));
    // prepare input data cache in device memory
    // 在Device侧申请预处理数据缓存
    CUDA_CHECK(cudaMalloc((void**)&img_device, MAX_IMAGE_INPUT_SIZE_THRESH * 3));

    //输入图像预处理
    int fcount = 0;
    std::vector<cv::Mat> imgs_buffer(BATCH_SIZE);
    for (int f = 0; f < (int)file_names.size(); f++) {
        fcount++;
        if (fcount < BATCH_SIZE && f + 1 != (int)file_names.size()) continue;
        //auto start = std::chrono::system_clock::now();
        float* buffer_idx = (float*)buffers[inputIndex];
        for (int b = 0; b < fcount; b++) {
            cv::Mat img = cv::imread(img_dir + "/" + file_names[f - fcount + 1 + b]);
            if (img.empty()) continue;
            imgs_buffer[b] = img;
            size_t  size_image = img.cols * img.rows * 3;
            size_t  size_image_dst = INPUT_H * INPUT_W * 3;
            //copy data to pinned memory
            memcpy(img_host,img.data,size_image);   //拷贝预处理数据到HOST侧
            //copy data to device memory    
            CUDA_CHECK(cudaMemcpyAsync(img_device,img_host,size_image,cudaMemcpyHostToDevice,stream));  //拷贝预处理数据到Device侧
            preprocess_kernel_img(img_device, img.cols, img.rows, buffer_idx, INPUT_W, INPUT_H, stream);       
            buffer_idx += size_image_dst;
        }


        // Run inference
        // 执行推理
        auto start = std::chrono::system_clock::now();  //计时开始
        doInference(*context, stream, (void**)buffers, prob, BATCH_SIZE);  //context为推理的上下文环境,stream为注册流(用于异步推理时进行同步),buffers为传入的图像数据,prob为推理的结果
        auto end = std::chrono::system_clock::now();    
        std::cout << "inference time: " << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count() << "ms" << std::endl;
        std::vector<std::vector<Yolo::Detection>> batch_res(fcount);

        //后处理
        for (int b = 0; b < fcount; b++) {
            auto& res = batch_res[b];
            nms(res, &prob[b * OUTPUT_SIZE], CONF_THRESH, NMS_THRESH);  //进行非极大值抑制后res中保留着结果
        }
        //根据非极大值抑制的结果标注相关信息(画框,文字信息等)
        for (int b = 0; b < fcount; b++) {
            auto& res = batch_res[b];
            cv::Mat img = imgs_buffer[b];
            for (size_t j = 0; j < res.size(); j++) {
                cv::Rect r = get_rect(img, res[j].bbox);
                cv::rectangle(img, r, cv::Scalar(0x27, 0xC1, 0x36), 2);
                cv::putText(img, std::to_string((int)res[j].class_id), cv::Point(r.x, r.y - 1), cv::FONT_HERSHEY_PLAIN, 1.2, cv::Scalar(0xFF, 0xFF, 0xFF), 2);
            }
            cv::imwrite("_" + file_names[f - fcount + 1 + b], img);
        }
        fcount = 0;
    }

    // Release stream and buffers
    cudaStreamDestroy(stream);
    CUDA_CHECK(cudaFree(img_device));   //释放cuda流
    CUDA_CHECK(cudaFreeHost(img_host));     //释放HOST端内存
    CUDA_CHECK(cudaFree(buffers[inputIndex]));  //释放设备端内存
    CUDA_CHECK(cudaFree(buffers[outputIndex]));
    // Destroy the engine
    context->destroy(); //析构engine引擎资源
    engine->destroy();
    runtime->destroy();


    // Print histogram of the output distribution
    //std::cout << "\nOutput:\n\n";
    //for (unsigned int i = 0; i < OUTPUT_SIZE; i++)
    //{
    //    std::cout << prob[i] << ", ";
    //    if (i % 10 == 0) std::cout << std::endl;
    //}
    //std::cout << std::endl;

    return 0;
}