494 lines
26 KiB
C++
494 lines
26 KiB
C++
|
#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;
|
|||
|
|
}
|