Cpp DenseNet OpenVino CMake工程

Cpp OpenVino CMake

Python版本导引

• Python DenseNet OpenVino导出
• Python DenseNet OpenVino推理
• Python DenseNet OpenVino打包

CMake工程示例

测试性质的工程结构如下:

Project:

• Network: 存放网络推理相关
  • DebugTools: 打印网络结构
  • DenseGradeWrapper: 推理主结构
  • NetworkTools: 部分CV辅助函数
• Script: 存放前面博客中的导出以及验证Py文件
  • Cpp DenseNet OpenVino导出
  • Cpp DenseNet OpenVino测试
• CMakeLists.txt: cmake工程文件
• main.cpp: 简单的执行文件

CMake示例

OpenCV和OpenVINO的CMake引入都比较简单，本身框架也比较规范，在后面将会编写Tensorrt版本的博客，相对来说CMake就要复杂一点

CMake只要链接openvino::runtime就可轻松包含OpenVINO的头文件和lib相关位置，如果无法编译，请手动链接静态库版本，这也是Windows的通病了，Linux下推荐链接动态库

如果不需要使用Qt的相关库，可以自行删除，个人使用OpenVINO主要集成于Qt，所以直接使用Qt的默认配置进行了添加修改

cmake_minimum_required(VERSION 3.14)

project(openvino-cpu-win-msvc2019 LANGUAGES CXX)

set(CMAKE_AUTOUIC ON)
set(CMAKE_AUTOMOC ON)
set(CMAKE_AUTORCC ON)

set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)

# find openvino
set(OpenVINO_DIR "C:/Program Files (x86)/Intel/openvino_2024/runtime/cmake")
set(OpenCV_DIR "C:/Program Files/opencv460/build/x64/vc15/lib")

find_package(OpenCV)
find_package(OpenVINO REQUIRED COMPONENTS Runtime)

# find qt core
find_package(QT NAMES Qt6 Qt5 REQUIRED COMPONENTS Core)
find_package(Qt${QT_VERSION_MAJOR} REQUIRED COMPONENTS Core)

add_executable(openvino-cpu-win-msvc2019
  main.cpp
  Network/DebugTools.h Network/DebugTools.cpp
  Network/NetworkTools.h Network/NetworkTools.cpp
  Network/DenseGradeWrapper.h Network/DenseGradeWrapper.cpp
)

target_include_directories(openvino-cpu-win-msvc2019
    PRIVATE
        ${OpenCV_INCLUDE_DIRS}
        .
)

target_link_libraries(openvino-cpu-win-msvc2019
    Qt${QT_VERSION_MAJOR}::Core
    openvino::runtime
    ${OpenCV_LIBS}
)

include(GNUInstallDirs)
install(TARGETS openvino-cpu-win-msvc2019
    LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
    RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
)