泰州建站程序,营销软文代写,大型网站建设公司,浙江华纳建设有限公司网站最近这一个月在研究国产瑞芯微板子上部署yolov8的检测和分割模型#xff0c;踩了很多坑#xff0c;记录一下部署的过程和遇到的一些问题#xff1a;
1 环境搭建
需要的环境和代码主要包括#xff1a; #xff08;1#xff09;rknn-toolkit2-1.5.2#xff1a;工具链踩了很多坑记录一下部署的过程和遇到的一些问题
1 环境搭建
需要的环境和代码主要包括 1rknn-toolkit2-1.5.2工具链开发环境 2rockchip-yolov8pt模型转onnx模型 3yolov8_onnx2rknn在2的基础上转检测rknn模型 4yolov8seg_onnx2rknn在2的基础上转分割rknn模型 最好使用对应的环境环境不匹配的话会出现很多问题。
2 ubuntu docker环境
Docker容器主要用来进行模型转换也就是pt转onnx的过程因此docker中需要用的的包主要是rockchip-yolov8,需要修改该代码进行模型的转换在linux服务器上安装docker环境创建一个ubuntu系统的docker环境 这一部分的修改代码参考山水无移大哥的部署过程贼清洗膜拜一下少走了很多弯路直接贴上地址。
3 模型转换问题
在转自己的pt到onnx模型时容易出现以下问题 1报错信息
copying a param with shape torch.Size([64,64,3,3]) from checkpoint,the shape in current model is torch.Size(32,64,3,3)主要的问题有两种 1在最后一步导出onnx时yolov8s.yaml里面没有修改成自己的模型的类别信息 2自己训练的yolov8m模型但是选择的yaml是yolov8s.yaml from ultralytics import YOLO# model YOLO(/cytech_ai/sipingtest/rknntest/model/20230228_yolov8_LiftPerson_filter.pt)
# results model(taskdetect, modepredict, source/cytech_ai/sipingtest/rknntest/2.jpg, line_thickness3, saveTrue, devicecpu)model YOLO(/cytech_ai/sipingtest/rknntest/rockchip-yolov8/ultralytics/cfg/models/v8/yolov8s.yaml)
results model(taskdetect, modepredict, source/cytech_ai/sipingtest/rknntest/2.jpg, line_thickness3, saveTrue, devicecpu)2多处修改时最终的输出结果和分割模型的结果搞混了导致模型输出对应不上
4 RK3588上环境搭建
瑞芯微rk3588上需要的环境主要是rknpu2主要用来C编写cmakelists文件时导入动态库和头文件我这里将检测模型和分割模型全部集成到一个工程里面分享一个个人的cmakelist文件
cmake_minimum_required(VERSION 3.4.1)# 声明一个 cmake 工程
set(PROJECT_NAME rknn_yolov8_AlgDetectModel)
project(${PROJECT_NAME})set(CMAKE_CXX_STANDARD 11)set(TARGET_SOC rk3588)
set(CMAKE_C_COMPILER aarch64)# rknn api
if(TARGET_SOC STREQUAL rk356x)set(RKNN_API_PATH ${CMAKE_SOURCE_DIR}/../../runtime/RK356X/${CMAKE_SYSTEM_NAME}/librknn_api)set(RKNN_API_PATH ${CMAKE_SOURCE_DIR}/../../runtime/RK356X/${CMAKE_SYSTEM_NAME}/librknn_api)
elseif(TARGET_SOC STREQUAL rk3588)set(RKNN_API_PATH /home/siping/testrknn/rknpu2-1.5.2/runtime/RK3588/Linux/librknn_api/aarch64)
else()message(FATAL_ERROR TARGET_SOC is not set, ref value: rk356x or rk3588 or rv110x)
endif()if (CMAKE_SYSTEM_NAME STREQUAL Android)set(RKNN_RT_LIB ${RKNN_API_PATH}/${CMAKE_ANDROID_ARCH_ABI}/librknnrt.so)
else()if (CMAKE_C_COMPILER MATCHES aarch64)set(LIB_ARCH aarch64)else()set(LIB_ARCH armhf)endif()#直接链接这个库了set(RKNN_RT_LIB /home/siping/testrknn/rknpu2-1.5.2/runtime/RK3588/Linux/librknn_api/aarch64/librknnrt.so)
endif()#链接头文件
include_directories(/home/siping/testrknn/rknpu2-1.5.2/runtime/RK3588/Linux/librknn_api/include)#第三方依赖库
include_directories(${CMAKE_SOURCE_DIR}/../3rdparty)# opencv
#if (CMAKE_SYSTEM_NAME STREQUAL Android)
# set(OpenCV_DIR ${CMAKE_SOURCE_DIR}/../3rdparty/opencv/OpenCV-android-sdk/sdk/native/jni/abi-${CMAKE_ANDROID_ARCH_ABI})
#else()
# if(LIB_ARCH STREQUAL armhf)
# set(OpenCV_DIR ${CMAKE_SOURCE_DIR}/../3rdparty/opencv/opencv-linux-armhf/share/OpenCV)
# else()
# set(OpenCV_DIR ${CMAKE_SOURCE_DIR}/../3rdparty/opencv/opencv-linux-aarch64/share/OpenCV)
# endif()
#endif()
#find_package(OpenCV REQUIRED)#手动链接opencv480
set(OpenCV_DIR /home/siping/thirdparty/opencv480/)
set(OpenCV_INCLUDE_DIRS /home/siping/thirdparty/opencv480/include/opencv4)
set(OpenCV_LDFLAGS /home/siping/thirdparty/opencv480/lib)include_directories(${OpenCV_INCLUDE_DIRS})
link_directories(${OpenCV_LDFLAGS})message(STATUS OpenCV library status:)message(STATUS version: ${OpenCV_VERSION})
message(STATUS include path: ${OpenCV_INCLUDE_DIRS})
message(STATUS libraries: ${OpenCV_LDFLAGS})#rga
if(TARGET_SOC STREQUAL rk356x)set(RGA_PATH ${CMAKE_SOURCE_DIR}/../3rdparty/rga/RK356X)
elseif(TARGET_SOC STREQUAL rk3588)set(RGA_PATH ${CMAKE_SOURCE_DIR}/../3rdparty/rga/RK3588)
else()message(FATAL_ERROR TARGET_SOC is not set, ref value: rk356x or rk3588)
endif()
if (CMAKE_SYSTEM_NAME STREQUAL Android)set(RGA_LIB ${RGA_PATH}/lib/Android/${CMAKE_ANDROID_ARCH_ABI}/librga.so)
else()if (CMAKE_C_COMPILER MATCHES aarch64)set(LIB_ARCH aarch64)else()set(LIB_ARCH armhf)endif()#链接库就这一个set(RGA_LIB ${RGA_PATH}/lib/Linux//${LIB_ARCH}/librga.so)
endif()
include_directories( ${RGA_PATH}/include)#瑞芯微 glog日志库
set(GLOG_INCLUDE /home/siping/thirdparty/glog_arm64/include/)
set(GLOG_LIB /home/siping/thirdparty/glog_arm64/lib)include_directories(${GLOG_INCLUDE})
link_directories(${GLOG_LIB})message(STATUS GLOG library status:)
message(STATUS include path: ${GLOG_INCLUDE})
message(STATUS libraries: ${GLOG_LIB})#链接头文件
include_directories( ${CMAKE_SOURCE_DIR}/include)#链接cpp文件
aux_source_directory(src DIR_CPP)## install target and libraries 将所有需要的依赖库放在同一个位置
#set install path
set(CMAKE_BUILD_RPATH ${OpenCV_LDFLAGS})
set(CMAKE_INSTALL_PREFIX /home/siping/algunion/alglib)
message(STATUS CMAKE_INSTALL_PREFIX ${CMAKE_INSTALL_PREFIX})# set runtime path
set(CMAKE_INSTALL_RPATH .)# 如果想生成动态库SHARE .so
#add_library(${PROJECT_NAME} SHARED ${DIR_CPP})
#set(${PROJECT_NAME} PROPERTIES OUTPUT_NAME ${PROJECT_NAME})
add_executable(${PROJECT_NAME} src/main.cc ${DIR_CPP})target_link_libraries(${PROJECT_NAME}${RKNN_RT_LIB} #必须的runtime librknnrt.so${RGA_LIB} #rga librga.so${OpenCV_LDFLAGS}-lopencv_world${GLOG_LIB}-lglog)install(TARGETS ${PROJECT_NAME} DESTINATION ${CMAKE_INSTALL_PREFIX})file(GLOB GLOG_LIB ${GLOG_LIB}/lib*.so.*)
file(GLOB OpenCV_LDFLAGS ${OpenCV_LDFLAGS}/lib*.so.*)install(PROGRAMS${OpenCV_LDFLAGS}${RKNN_RT_LIB}${RGA_LIB}${GLOG_LIB}DESTINATION ${CMAKE_INSTALL_PREFIX})install(DIRECTORY model DESTINATION /home/siping/algunion)
前面用到的环境和代码打个包上传到了百度网盘C的部署的代码参考的里面都有我自己这边只是根据自己的项目做了集成如有需要可私信。
5 参考
检测模型https://blog.csdn.net/zhangqian_1/article/details/135523096?spm1001.2014.3001.5502 分割模型https://blog.csdn.net/zhangqian_1/article/details/131571838?spm1001.2014.3001.5502
另外一种部署方法仅检测模型Python https://blog.csdn.net/m0_48979117/article/details/135628375
