jetsonTX2 nx配置tensorRT加速yolov5推理

环境说明

Ubuntu 18+conda环境python3.9+cuda10.2，硬件平台是Jetson tx2 nx
前提你已经能运行YOLOV5代码后，再配置tensorRT进行加速。
目前只试了图片检测和C++打开USB摄像头进行视频检测，希望是使用python配合D435i深度相机来实现检测，后续再更新。

一、安装TensorRT

1. 安装git和cmake（已经安装了忽略这一步）

sudo apt-get install libpython3-dev python3-numpy

2. 克隆源码
   连接不上就挂个梯子

git clone https://github.com/dusty-nv/jetson-inference

3. 安装附属文件

git submodule update --init

4. 添加jetson-inference需要的包

• 先下载相关包：百度网盘分享 提取码：s75z
  下载后拷贝到jetson tx2中，将所有包复制到刚刚克隆的jetson-inference下的data/networks

• 然后cd进入到data/networks文件夹，解压相关包

cd jetson-inference/data/networks  
for tar in *.tar.gz; do tar xvf $tar; done

• 再编辑 jetson-inference/CMakePrebuild.sh文件，把./download-models.sh 注释掉
  

5. 编译

• 在 jetson-inference文件夹里面创建build文件夹

mkdir build

• 进入build中进行cmake

cd build
cmake ../

运行过程中弹出该页面跳过即可

cmake过程中报错，克隆不成功，就删除jetson-inference文件夹，再试一遍

• cmake成功后

# 可能有点慢，耐心等待
make 

make成功后

sudo make install

6. 测试
   安装成功后，进行测试

cd jetson-inference/build/aarch64/bin

./imagenet-console ./images/bird_0.jpg output.jpg

参考博主：https://blog.csdn.net/qq_42078934/article/details/129669965?spm=1001.2014.3001.5506

• 如果出现在下载Googlenet.tar.gz相关，并且最终下载失败，报错，需要先中断执行；
• 然后在networks文件夹中新建Googlenet文件夹，将networks文件夹中的bvlc_googlenet.caffemodel、googlenet.prototxt和googlenet_noprob.prototxt剪切到新建的Googlenet文件夹；
• 最后在Googlenet文件夹新建networks文件夹，将ilsvrc12_synset_words.txt剪切到新建networks文件夹

再次进行测试：

二、TensorRT加速YOLOV5

1. 安装pycuda包
   这个包是使用python编写加速的一个包，本文还只实验了C++版本的，但可以先把这个包安装上

python3 -m pip install 'pycuda<2020.1'

用这个命令直接安装的2019.1版本的，网上有些教程是下载包再进行安装，我这样发现安装的包在虚拟环境中用不了，建议直接进入到需要安装的虚拟环境中，直接用这条命令进行安装。
安装完后测试：

2. 下载tensorrt的YOLOV5代码
   这里我是想把自己训练好的模型，用tensorrt做一个加速，自己训练模型的yolov5版本是6.0，所以这里也下载6.0版本的tensorrt yolov5。下载链接
   
3. 生成wts文件
   自己训练的模型是.pt，这里先转换成.wts文件。

• 把刚刚下载的tensorrt yolo文件中yolov5下的gen_wts.py复制到你自己yolov5代码的文件夹下（这里应该存放了你自己训练的.pt权重文件）
  
• 执行gen_wts.py生成.wts文件。

python3 gen_wts.py weights/yolov5s.pt # 后面是自己的权重的名字

这里如果遇到报错，参考解决办法：解决办法

4. 生成部署引擎

• 先将yolov5s.wts文件(上一步生成的文件)放到tensorrtx-yolov5-v6.0/yolov5文件夹中。
• 然后打开yololayer.h文件，修改num总数，根据你训练模型的类个数来，这里我是两类，所以改为2
  
• 编译相关

cd tensorrtx-yolov5-v6.0/yolov5
mkdir build
cd build
cmake ..
make

sudo ./yolov5 -s ../yolov5s.wts yolov5s.engine s 
# sudo ./yolov5 -s [.wts] [.engine] [s/m/l/x/s6/m6/l6/x6 or c/c6 gd gw]      
# s代表用的是yolov5s，是什么就改成什么

到这里便通过tensorrt生成了基于C++的engine部署引擎文件，后缀.engine

5. 使用图片测试
   将yolov5源代码的data文件夹中的images文件夹整个复制到tensorrtx/yolov5文件夹，在build文件夹里执行下面的代码。

sudo ./yolov5 -d yolov5s.engine ../samples
#sudo ./yolov5 -d [.engine] [image folder]

执行后，结果会在build中看到。如果图形没有画框，可能是因为s模型所产生的置信度一般在0.2-0.4之间，在yolov5.cpp文件中置信度conf_thresh设置在0.5，低于0.5的检测框会被排除。

6. 使用USB摄像头
   这里是采用的C++的版本，替换tensorrtx-yolov5-v6.0\yolov5\yolov5.cpp文件中的内容为（注意修改为自己的分类类别）：

#include <iostream>
#include <chrono>
#include "cuda_utils.h"
#include "logging.h"
#include "common.hpp"
#include "utils.h"
#include "calibrator.h"#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;//修改为自己的类别
char *my_classes[]={"person", "bicycle"};static int get_width(int x, float gw, int divisor = 8) {//return math.ceil(x / divisor) * divisorif (int(x * gw) % divisor == 0) {return int(x * gw);}return (int(x * gw / divisor) + 1) * divisor;
}static int get_depth(int x, float gd) {if (x == 1) {return 1;}else {return round(x * gd) > 1 ? round(x * gd) : 1;}
}//#创建engine和network
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_NAMEITensor* 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");// yolo layer 0IConvolutionLayer* 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");//yolo layer 1IConvolutionLayer* 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 enginebuilder->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);
#endifstd::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 morenetwork->destroy();// Release host memoryfor (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_NAMEITensor* 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 enginebuilder->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);
#endifstd::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 morenetwork->destroy();// Release host memoryfor (auto& mem : weightMap){free((void*)(mem.second.values));}return engine;
}void APIToModel(unsigned int maxBatchSize, IHostMemory** modelStream, float& gd, float& gw, std::string& wts_name) {// Create builderIBuilder* builder = createInferBuilder(gLogger);IBuilderConfig* config = builder->createBuilderConfig();// Create model to populate the network, then set the outputs and create an engineICudaEngine* engine = build_engine(maxBatchSize, builder, config, DataType::kFLOAT, gd, gw, wts_name);assert(engine != nullptr);// Serialize the engine(*modelStream) = engine->serialize();// Close everything downengine->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 hostCUDA_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) {if (argc < 3) return false;if (std::string(argv[1]) == "-v" && argc == 3) {engine = std::string(argv[2]);}else {return false;}return true;
}int main(int argc, char** argv) {cudaSetDevice(DEVICE);//std::string wts_name = "";std::string engine_name = "";//float gd = 0.0f, gw = 0.0f;//std::string img_dir;if (!parse_args(argc, argv, engine_name)) {std::cerr << "arguments not right!" << std::endl;std::cerr << "./yolov5 -v [.engine] // run inference with camera" << std::endl;return -1;}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 deviceCUDA_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 streamcudaStream_t stream;CUDA_CHECK(cudaStreamCreate(&stream));//#读取本地视频//cv::VideoCapture capture("/home/nano/Videos/video.mp4");//#调用本地usb摄像头,我的默认参数为1,如果1报错,可修改为0.cv::VideoCapture capture(0);if (!capture.isOpened()) {std::cout << "Error opening video stream or file" << std::endl;return -1;}int key;int fcount = 0;while (1){cv::Mat frame;capture >> frame;if (frame.empty()){std::cout << "Fail to read image from camera!" << std::endl;break;}fcount++;//if (fcount < BATCH_SIZE && f + 1 != (int)file_names.size()) continue;for (int b = 0; b < fcount; b++) {//cv::Mat img = cv::imread(img_dir + "/" + file_names[f - fcount + 1 + b]);cv::Mat img = frame;if (img.empty()) continue;cv::Mat pr_img = preprocess_img(img, INPUT_W, INPUT_H); // letterbox BGR to RGBint 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[b * 3 * INPUT_H * INPUT_W + i] = (float)uc_pixel[2] / 255.0;data[b * 3 * INPUT_H * INPUT_W + i + INPUT_H * INPUT_W] = (float)uc_pixel[1] / 255.0;data[b * 3 * INPUT_H * INPUT_W + i + 2 * INPUT_H * INPUT_W] = (float)uc_pixel[0] / 255.0;uc_pixel += 3;++i;}}}// Run inferenceauto start = std::chrono::system_clock::now();//#获取模型推理开始时间doInference(*context, stream, buffers, data, prob, BATCH_SIZE);auto end = std::chrono::system_clock::now();//#结束时间//std::cout << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count() << "ms" << std::endl;int fps = 1000.0 / std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count();std::vector<std::vector<Yolo::Detection>> batch_res(fcount);for (int b = 0; b < fcount; b++) {auto& res = batch_res[b];nms(res, &prob[b * OUTPUT_SIZE], CONF_THRESH, NMS_THRESH);}for (int b = 0; b < fcount; b++) {auto& res = batch_res[b];//std::cout << res.size() << std::endl;//cv::Mat img = cv::imread(img_dir + "/" + file_names[f - fcount + 1 + b]);for (size_t j = 0; j < res.size(); j++) {cv::Rect r = get_rect(frame, res[j].bbox);cv::rectangle(frame, r, cv::Scalar(0x27, 0xC1, 0x36), 2);std::string label = my_classes[(int)res[j].class_id];cv::putText(frame, label, cv::Point(r.x, r.y - 1), cv::FONT_HERSHEY_PLAIN, 1.2, cv::Scalar(0xFF, 0xFF, 0xFF), 2);std::string jetson_fps = "FPS: " + std::to_string(fps);cv::putText(frame, jetson_fps, cv::Point(11, 80), cv::FONT_HERSHEY_PLAIN, 3, cv::Scalar(0, 0, 255), 2, cv::LINE_AA);}//cv::imwrite("_" + file_names[f - fcount + 1 + b], img);}cv::imshow("yolov5", frame);key = cv::waitKey(1);if (key == 'q') {break;}fcount = 0;}capture.release();// Release stream and bufferscudaStreamDestroy(stream);CUDA_CHECK(cudaFree(buffers[inputIndex]));CUDA_CHECK(cudaFree(buffers[outputIndex]));// Destroy the enginecontext->destroy();engine->destroy();runtime->destroy();return 0;
}

修改完后执行：

cd build
make
sudo ./yolov5 -v yolov5s.engine # 后面是自己生成的部署引擎文件

基于python的有时间了再弄