网站开发合同模版,电商购物网站建设,湖南领企信息科技有限公司,网络服务停用写目录 yolov8 模型部署--TensorRT部署1、模型导出为onnx格式2、模型onnx格式转engine 部署 yolov8 模型部署–TensorRT部署
1、模型导出为onnx格式 如果要用TensorRT部署YOLOv8#xff0c;需要先使用下面的命令将模型导出为onnx格式#xff1a; yolo export modelyolov8n.p… 写目录 yolov8 模型部署--TensorRT部署1、模型导出为onnx格式2、模型onnx格式转engine 部署 yolov8 模型部署–TensorRT部署
1、模型导出为onnx格式 如果要用TensorRT部署YOLOv8需要先使用下面的命令将模型导出为onnx格式 yolo export modelyolov8n.pt formatonnx YOLOv8的3个检测头一共有80x8040x4020x208400个输出单元格每个单元格包含x,y,w,h这4项再加80个类别的置信度总共84项内容所以通过上面命令导出的onnx模型的输出维度为1x84x8400。 模型输出维度 这样的通道排列顺序有个问题那就是后处理的时候会造成内存访问不连续。 为了解决这个问题我们可以修改一下代码具体做法是把ultralytics/nn/modules.py文件中的代码做如下修改交换一下张量y的通道顺序 def forward(self, x):shape x[0].shape # BCHWfor i in range(self.nl):x[i] torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)if self.training:return xelif self.dynamic or self.shape ! shape:self.anchors, self.strides (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))self.shape shapex_cat torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)if self.export and self.format in (saved_model, pb, tflite, edgetpu, tfjs): # avoid TF FlexSplitV opsbox x_cat[:, :self.reg_max * 4]cls x_cat[:, self.reg_max * 4:]else:box, cls x_cat.split((self.reg_max * 4, self.nc), 1)dbox dist2bbox(self.dfl(box), self.anchors.unsqueeze(0), xywhTrue, dim1) * self.stridesy torch.cat((dbox, cls.sigmoid()), 1)# 修改模型输出维度yy.permute(0,2,1)return y if self.export else (y, x)这样修改后再执行上面的模型导出命令模型的输出维度变为1x8400x84
2、模型onnx格式转engine 部署
配置好TensorRT和NVIDIA环境使用trtexec 转换格式trtexec --onnxcoco/best.onnx --saveEnginecoco/best.onnx.engine --workspace32 模型部署部分代码-c#ifndef MyController_hpp
#define MyController_hpp#include ctime
#include chrono
#include sstream
#include iomanip#include iostream
#include numeric
#include vector#include oatpp/web/server/api/ApiController.hpp
#include oatpp/core/macro/codegen.hpp
#include oatpp/core/macro/component.hpp#include opencv2/opencv.hpp
#include ../dto/DTOs.hpp // 定义数据格式用于在不同组件之间传输数据#include ../yoloApp/simple_yolo.hpp
#include ../byteTrackApp/logging.h
#include ../byteTrackApp/BYTETracker.h// high performance
#include ../yoloHighPer/cpm.hpp
#include ../yoloHighPer/infer.hpp
#include ../yoloHighPer/yolo.hpp# include dirent.h
# include sys/types.h
# include sys/stat.h
# include unistd.h
# include stdarg.husing namespace std;
using namespace cv;#include OATPP_CODEGEN_BEGIN(ApiController) //-- Begin Codegenstatic bool exists(const string path){#ifdef _WIN32return ::PathFileExistsA(path.c_str());
#elsereturn access(path.c_str(), R_OK) 0;
#endif
}static std::vectorstd::string cocolabels {car, excavator, loader, dumpTruck, person
};class InferInstance{
public:InferInstance(std::string onnx_model_path, std::string trt_model_path){onnx_model onnx_model_path;trt_model trt_model_path;startup();}bool startup(){// if(!exists(trt_model)){// SimpleYolo::compile(// SimpleYolo::Mode::FP32, // FP32、FP16、INT8// SimpleYolo::Type::V8, // 1, // max batch size// onnx_model, // source // trt_model, // save to// 1 30,// inference// );// }infer_ yolo::load(trt_model, yolo::Type::V8);return infer_ ! nullptr;}int inference(const Mat image_input, yolo::BoxArray boxarray){if(infer_ nullptr){// INFOE(Not Initialize.);return 1;}if(image_input.empty()){// INFOE(Image is empty.);return 1;}boxarray infer_-forward(cvimg(image_input));return 0;}private:yolo::Image cvimg(const cv::Mat image) { return yolo::Image(image.data, image.cols, image.rows);}private:std::string onnx_model best.onnx;std::string trt_model best.onnx.engine;shared_ptryolo::Infer infer_;
};///
std::string onnx_model coco/best.onnx;
std::string engine_label coco/best.onnx.engine;
std::unique_ptrInferInstance infer_instance1(new InferInstance(onnx_model, engine_label));int frame_rate 10;
int track_buffer 30;
std::unique_ptrBYTETracker tracker_instance1(new BYTETracker(frame_rate, track_buffer));////*** 建议使用 Api 控制器而不是使用裸 HttpRequestHandler 为每个新端点创建新的请求处理程序。* API 控制器通过为您生成样板代码使添加新端点的过程变得更加容易。 它还有助于组织您的端点* 将它们分组到不同的 API 控制器中。*//*** Sample Api Controller.*/
class MyController : public oatpp::web::server::api::ApiController {
protected:/*** Constructor with object mapper.* param objectMapper - default object mapper used to serialize/deserialize DTOs.*/MyController(const std::shared_ptrObjectMapper objectMapper): oatpp::web::server::api::ApiController(objectMapper){}public: static std::shared_ptrMyController createShared(OATPP_COMPONENT(std::shared_ptrObjectMapper, objectMapper)){return std::shared_ptrMyController(new MyController(objectMapper));}// TODO Insert Your endpoints here !!!/--data--// 多目标追踪ENDPOINT_ASYNC(POST, /car1, tracker1){ENDPOINT_ASYNC_INIT(tracker1)Action act() override {return request-readBodyToStringAsync().callbackTo(tracker1::returnResponse);}Action returnResponse(const oatpp::String body_){auto response tracker_inference(*infer_instance1, *tracker_instance1, body_, controller);return _return(response);}};//public:// 多目标追踪static std::shared_ptrOutgoingResponse tracker_inference(InferInstance infer_, BYTETracker track_infer, std::string body_, auto* controller){auto base64Image base64_decode(body_);if(base64Image.empty()){return controller-createResponse(Status::CODE_400, The image is empty!);}std::vectorchar base64_img(base64Image.begin(), base64Image.end());cv::Mat image cv::imdecode(base64_img, 1);// 获取程序开始时间点auto start_time std::chrono::high_resolution_clock::now();// 推理yolo::BoxArray boxarray;CV_Assert(0 infer_.inference(image, boxarray));// 获取程序结束时间点auto end_time std::chrono::high_resolution_clock::now();// 计算运行时间auto duration std::chrono::duration_caststd::chrono::milliseconds(end_time - start_time);// 打印运行时间以微秒为单位// std::cout 程序运行时间: duration.count() 毫秒 std::endl;// 结果处理vectorObjects objects;objects.resize(boxarray.size());int index 0;for(auto box : boxarray) {objects[index].rect.x box.left;;objects[index].rect.y box.top;objects[index].rect.width box.right - box.left;objects[index].rect.height box.bottom - box.top;objects[index].prob box.confidence;objects[index].label box.class_label;index;std::cout left: box.left , top: box.top , right: box.right , bottom: box.bottom , confidence: box.confidence , class_label: box.class_label std::endl;}auto yoloDto TrackYoloDto::createShared();auto boxList TrackBoxList::createShared();std::vectorSTrack output_stracks track_infer.update(objects);for (int i 0; i output_stracks.size(); i){auto trackBoxDto TrackerBboxes::createShared();vectorfloat tlwh output_stracks[i].tlwh; // 方框的位置trackBoxDto-class_id cocolabels[output_stracks[i].class_id];trackBoxDto-track_id output_stracks[i].track_id;trackBoxDto-x tlwh[0];trackBoxDto-y tlwh[1];trackBoxDto-width tlwh[2];trackBoxDto-height tlwh[3];boxList-push_back(trackBoxDto);}output_stracks.clear();yoloDto-data boxList;yoloDto-status successful;yoloDto-time currentDateTime();return controller-createDtoResponse(Status::CODE_200, yoloDto);}static std::string currentDateTime(){auto now std::chrono::system_clock::now();auto now_c std::chrono::system_clock::to_time_t(now);auto now_ms std::chrono::duration_caststd::chrono::milliseconds(now.time_since_epoch()) % 1000;std::stringstream ss;ss std::put_time(std::localtime(now_c), %Y-%m-%d %H:%M:%S) . std::setfill(0) std::setw(3) now_ms.count();return ss.str();}static unsigned char from_b64(unsigned char ch){/* Inverse lookup map */static const unsigned char tab[128] {255, 255, 255, 255,255, 255, 255, 255, /* 0 */255, 255, 255, 255,255, 255, 255, 255, /* 8 */255, 255, 255, 255,255, 255, 255, 255, /* 16 */255, 255, 255, 255,255, 255, 255, 255, /* 24 */255, 255, 255, 255,255, 255, 255, 255, /* 32 */255, 255, 255, 62,255, 255, 255, 63, /* 40 */52, 53, 54, 55,56, 57, 58, 59, /* 48 */60, 61, 255, 255,255, 200, 255, 255, /* 56 is 200, on index 61 */255, 0, 1, 2,3, 4, 5, 6, /* 64 */7, 8, 9, 10,11, 12, 13, 14, /* 72 */15, 16, 17, 18,19, 20, 21, 22, /* 80 */23, 24, 25, 255,255, 255, 255, 255, /* 88 */255, 26, 27, 28,29, 30, 31, 32, /* 96 */33, 34, 35, 36,37, 38, 39, 40, /* 104 */41, 42, 43, 44,45, 46, 47, 48, /* 112 */49, 50, 51, 255,255, 255, 255, 255, /* 120 */};return tab[ch 127];}static std::string base64_decode(const std::string base64){if(base64.empty())return ;int len base64.size();auto s (const unsigned char*)base64.data();unsigned char a, b, c, d;int orig_len len;int dec_len 0;string out_data;auto end_s s base64.size();int count_eq 0;while(*--end_s ){count_eq ;}out_data.resize(len / 4 * 3 - count_eq);char *dst const_castchar*(out_data.data());char *orig_dst dst;while (len 4 (a from_b64(s[0])) ! 255 (b from_b64(s[1])) ! 255 (c from_b64(s[2])) ! 255 (d from_b64(s[3])) ! 255) {s 4;len - 4;if (a 200 || b 200) break; /* cant be there */*dst a 2 | b 4;if (c 200) break;*dst b 4 | c 2;if (d 200) break;*dst c 6 | d;}dec_len (dst - orig_dst);// dec_len必定等于out_data.size()return out_data;}
};#include OATPP_CODEGEN_END(ApiController) //-- End Codegen#endif /* MyController_hpp */ 启动模型 请求接口进行推理 yolov8 模型部署测试
