瑞芯微RK3588 C++部署Yolov8检测和分割模型-Toy模板网

这篇具有很好参考价值的文章主要介绍了瑞芯微RK3588 C++部署Yolov8检测和分割模型。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

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，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：
（1）rknn-toolkit2-1.5.2：工具链，开发环境
（2）rockchip-yolov8：pt模型转onnx模型
（3）yolov8_onnx2rknn：在（2）的基础上转检测rknn模型
（4）yolov8seg_onnx2rknn：在（2）的基础上转分割rknn模型
yolov8-seg 在rk3588上进行c++部署,瑞芯微RK3588,深度学习,目标分割,c++,YOLO
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)

yolov8-seg 在rk3588上进行c++部署,瑞芯微RK3588,深度学习,目标分割,c++,YOLO
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(task='detect', mode='predict', source='/cytech_ai/sipingtest/rknntest/2.jpg', line_thickness=3, save=True, device='cpu')

model = YOLO('/cytech_ai/sipingtest/rknntest/rockchip-yolov8/ultralytics/cfg/models/v8/yolov8s.yaml')
results = model(task='detect', mode='predict', source='/cytech_ai/sipingtest/rknntest/2.jpg', line_thickness=3, save=True, device='cpu')

（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：
yolov8-seg 在rk3588上进行c++部署,瑞芯微RK3588,深度学习,目标分割,c++,YOLO

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?spm=1001.2014.3001.5502
分割模型：https://blog.csdn.net/zhangqian_1/article/details/131571838?spm=1001.2014.3001.5502

另外一种部署方法，仅检测模型（Python）：
https://blog.csdn.net/m0_48979117/article/details/135628375文章来源地址https://www.toymoban.com/news/detail-845695.html

到了这里，关于瑞芯微RK3588 C++部署Yolov8检测和分割模型的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！