本篇是系列教程记录第二篇,主要讲述基于jetson NX开发板进行yolov5的一个部署。
在部署环境之前,首先进行开发板的刷机处理,本人参考的某位大佬的部署教程,传送门在这,大家亦可参考,这里不过多介绍。
在刷完机,应该显示的是Ubuntu18.04的版本,现在开始部署yolov5的环境,和之前一样,本文采用的4.0的版本,各位可以根据各自需求选择相应的版本。
在部署环境之前,本人强调希望不要构建conda环境,因为架构的原因,部署conda环境时,可能会出现各类第三方库无法安装,或者安装好找不到的现象。
这里直接建议直接在原生的python3.6的环境进行安装(这里强调一定是python3.6版本)因为英伟达官方只给出了3.6版本的torch编译版本。
首先是matplotlib包安装,若使用
pip install matplotlib
进行安装,大概率是会报错的,其原因就是架构问题,需要为开发板的arrch架构重新编译wheel,本文提供两种方法,建议使用第二种。
不使用pip进行安装,使用系统安装指令进行,但这样无法确定版本号
sudo apt-get install python3-matplotlib
直接下载以及编译好的wheel,直接进行build,这里提供我下载好的3.3.3版本,传送门在这提取码:5tlq
pip install matplotlib-3.3.3-cp36-cp36m-linux_aarch64.whl
安装pytorch是,千万不要使用pip install torch 这个指令,虽然使用这个指令也可以安装上,但是在后续使用时会出现cuda unavailable的情况,无法使用GPU,因此需要同安装matplotlib一样,下载编译好的wheel进行安装,由于nvidia官方只给出了python3.6版本的wheel,这就是为什么之前强调一定使用python3.6版本的原因,如果是其他版本的python则需要重新编译,大概耗时五到六个小时,且不保证一定会编译正确。
这里提供官方的下载地址传送门在这里面有torch各个版本的下载地址,但是貌似需要梯子才能下载。这里我也提供本人所下载的torch1.8版本wheel,传送门在这torch-1.8.0-cp36-cp36m-linux_aarch64.whl 提取码:s92e
pip install torch-1.8.0-cp36-cp36m-linux_aarch64.whl
安装好torch后,需要安装对应版本的torchvision,具体对应的版本在这里下载https://github.com/pytorch/vision
在对应的tag中选择你要下载的版本,下载好后直接cd到文件夹中,进行安装
cd torchvision
sudo python3 setup.py install
如果出现illegal instruction,只需在后面加上–user就好了。
python3 setup.py install --user
至此torch安装完成。
测试一下
输入python或者python3打开python编辑器
import torch
torch.__version__
import torchvision
torchvision.__version__
torch.cuda.is_available()
如果结果都对应上了,恭喜你安装成功。
如果遇到OSError: libmpi_cxx.so.20: cannot open shared object file: No such file or directory这类问题,这里有解决方案,传送门在这。
如果其他库也顺利安装上了,至此就可以开始在开发板上进行原生yolov5的测试了。
刷完机后开发板Jetpack本身自带tensorRT,这个可以通过这个链接进行查看,传送门在这。
下面就可以部署tensorRT加速了,这里感谢wangxinyu大佬做好的各个网络的加速版本,传送门在这,大家可以找自己的想要的版本。
按照这里面的教程应该就可以实现yolov5的部署,但是这里面只有对图片进行检测,本人稍加修改加入了视频检测的功能。传送门在这
主要修改了yolov5.cpp,暂且记为yolov5_v.cpp
#include
#include
#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;
char *my_classes[]={"healthy","scab","rust"}//修改为自己的标签
static int get_width(int x, float gw, int divisor = 8) {
//return math.ceil(x / divisor) * divisor
if (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;
}
}
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& wts, std::string& engine, bool& is_p6, float& gd, float& gw, std::string& img_dir, std::string& vedio_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] == '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") {
engine = std::string(argv[2]);
auto img_v_dir = std::string(argv[3]);
if (img_v_dir[0]=='i'){
img_dir = std::string(argv[4]);
vedio_dir = "";
}
else if (img_v_dir[0]=='v'){
vedio_dir = std::string(argv[4]);
img_dir = "";
}
else {
return false;
}
} else {
return false;
}
return true;
}
int main(int argc, char** argv) {
cudaSetDevice(DEVICE);
std::string wts_name = "";
std::string engine_name = "";
bool is_p6 = false;
float gd = 0.0f, gw = 0.0f;
std::string img_dir;
std::string vedio_dir;
if (!parse_args(argc, argv, wts_name, engine_name, is_p6, gd, gw, img_dir, vedio_dir)) {
std::cerr << "arguments not right!" << std::endl;
std::cerr << "./yolov5 -s [.wts] [.engine] [s/m/l/x/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
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
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));
if(!img_dir.empty()){
std::vector<std::string> file_names;
if (read_files_in_dir(img_dir.c_str(), file_names) < 0) {
std::cerr << "read_files_in_dir failed." << std::endl;
return -1;
}
int fcount = 0;
for (int f = 0; f < (int)file_names.size(); f++) {
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]);
if (img.empty()) continue;
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[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 inference
auto start = std::chrono::system_clock::now();
doInference(*context, stream, buffers, data, prob, BATCH_SIZE);
// auto end = std::chrono::system_clock::now();
// std::cout << std::chrono::duration_cast(end - start).count() << "ms" << std::endl;
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);
}
auto end = std::chrono::system_clock::now();
std::cout << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count() << "ms" << std::endl;
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(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);
std::string label = my_classes[(int)res[j].class_id];
cv::putText(img, label, 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;
}
}
if(!vedio_dir.empty()){
//cv::VideoCapture capture(0);//'0,1,2...'represent the camera
cv::VideoCapture capture(vedio_dir);
//int fourcc = cv::VideoWriter::fourcc('M','J','P','G');
//capture.set(cv::CAP_PROP_FOURCC, fourcc);
if(!capture.isOpened()){
std::cout << "Error opening video stream or file" << std::endl;
return -1;
}
int key;
int fcount = 0;
cv::Mat frame;
while(1)
{
capture >> frame;
if(frame.empty())
{
std::cout << "Fail to read image from vedio!" << 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 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[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 inference
auto start = std::chrono::system_clock::now();
doInference(*context, stream, buffers, data, prob, BATCH_SIZE);
auto end = std::chrono::system_clock::now();
//std::cout << std::chrono::duration_cast(end - start).count() << "ms" << std::endl;
int fps = 1000.0/std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count();
std::cout<<"fps:"<<fps<<std::endl;
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 = "Jetson NX 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 buffers
cudaStreamDestroy(stream);
CUDA_CHECK(cudaFree(buffers[inputIndex]));
CUDA_CHECK(cudaFree(buffers[outputIndex]));
// Destroy the engine
context->destroy();
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;
}
具体编译流程请看传送门的readme。
./yolov5_v -s ../yolov5s.wts ../yolov5s.engine s
测试视频
./yolov5_v -d ../yolov5s.engine v ../test1.mp4
or 测试图片
./yolov5_v -d ../yolov5s.engine i ../smaple/
本文简单记录一下自己的jetson NX的部署流程,若有其他疑问欢迎大家批评指正!