### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/ppyoloe/cpp/CMakeLists.txt

Installs the built executable to the root directory and installs model files (bus.jpg, labels, and .rknn files) to a 'model' subdirectory.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bus.jpg DESTINATION model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/coco_80_labels_list.txt DESTINATION model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Basic CMake Project Setup

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/RetinaFace/cpp/CMakeLists.txt

Sets the minimum CMake version and project name. This is a standard starting point for any CMake project.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_retinaface_demo)
```

--------------------------------

### Install Targets and Files

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/wav2vec2/cpp/CMakeLists.txt

Defines installation rules for the executable, a sample WAV file, and RKNN model files.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.wav DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/clip/cpp/CMakeLists.txt

Defines how the built targets and associated files should be installed. This includes installing the executable, model files, and text assets to their respective destinations.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/text.txt DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/dog_224x224.jpg DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/LPRNet/cpp/CMakeLists.txt

Defines installation rules for the executable, a sample image, and all .rknn model files.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.jpg DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Install Executable and Model Files

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/zipformer/cpp/CMakeLists.txt

Defines installation rules for the built executable and associated model files. The executable is installed to the root destination, while model files (WAV, vocabulary, and RKNN models) are installed into a 'model' subdirectory.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.wav DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/vocab.txt DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/RetinaFace/cpp/CMakeLists.txt

Defines what files and targets to install. This includes the main executable and associated model files.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.jpg DESTINATION model)
set(file_path ${CMAKE_CURRENT_SOURCE_DIR}/../model/RetinaFace.rknn)
if (EXISTS ${file_path})
    install(FILES ${file_path} DESTINATION model)
endif()
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-Rec/cpp/CMakeLists.txt

Specifies the installation targets for the executable, model files, and associated resources.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.png DESTINATION model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Install Targets and Model Files

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolo11/cpp/CMakeLists.txt

Installs the main executable, the zero-copy executable (if built), and model-related files to their designated destinations. This prepares the application for deployment.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bus.jpg DESTINATION model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/coco_80_labels_list.txt DESTINATION model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install (FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/whisper/cpp/CMakeLists.txt

Installs the built executable to the root directory and copies model files (WAV, TXT, and RKNN) to a 'model' subdirectory. This ensures all necessary components are deployed correctly.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test_en.wav DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test_zh.wav DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/vocab_en.txt DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/vocab_zh.txt DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/mel_80_filters.txt DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5/cpp/CMakeLists.txt

Defines installation targets for the executable, model files, label list, and RKNN model files.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bus.jpg DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/coco_80_labels_list.txt DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_obb/cpp/CMakeLists.txt

Defines installation rules for the executable, test image, label list, and RKNN model files.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.jpg DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/yolov8_obb_labels_list.txt DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-System/cpp/CMakeLists.txt

Specifies the installation targets for the built executable and model files. The executable is installed to the root directory, and model files are placed in the 'model' subdirectory.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.jpg DESTINATION model)
set(file_path ${CMAKE_CURRENT_SOURCE_DIR}/../../PPOCR-Det/model/ppocrv4_det.rknn)
if (EXISTS ${file_path})
    install(FILES ${file_path} DESTINATION model)
endif()

set(file_path ${CMAKE_CURRENT_SOURCE_DIR}/../../PPOCR-Rec/model/ppocrv4_rec.rknn)
if (EXISTS ${file_path})
    install(FILES ${file_path} DESTINATION model)
endif()
```

--------------------------------

### Basic CMake Project Setup

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov7/cpp/CMakeLists.txt

Initializes the CMake build system for the rknn_yolov7_demo project, setting the minimum required version and project name.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_yolov7_demo)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_pose/cpp/CMakeLists.txt

Defines installation rules for the executable, model files (bus.jpg, labels, .rknn models), and configuration files to specific destinations.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bus.jpg DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/yolov8_pose_labels_list.txt DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Basic CMake Project Setup

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_pose/cpp/CMakeLists.txt

Initializes the CMake build system for the rknn_yolov8_pose_demo project, requiring at least version 3.10.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_yolov8_pose_demo)
```

--------------------------------

### Install Executable and Model Files

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/mms_tts/cpp/CMakeLists.txt

Installs the built executable to the root directory and model files to the 'model' subdirectory.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Basic CMake Project Setup

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolo11/cpp/CMakeLists.txt

Initializes the CMake project and sets the minimum required version. This is standard for all CMake projects.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_yolo11_demo)
```

--------------------------------

### Installing Executable and Model Assets

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yamnet/cpp/CMakeLists.txt

Defines installation rules. The executable is installed to the root directory. Model files ('test.wav', 'yamnet_class_map.txt', and all '.rknn' files) are installed into a 'model' subdirectory.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.wav DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/yamnet_class_map.txt DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Basic CMake Project Setup

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov10/cpp/CMakeLists.txt

Initializes the CMake build system for the YOLOv10 project and sets the minimum required version.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_yolov10_demo)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_seg/cpp/CMakeLists.txt

Defines installation targets for the executable, RKNN runtime library, and model-related files (images and labels) to specific destinations.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${LIBRKNNRT} DESTINATION lib)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bus.jpg DESTINATION model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/coco_80_labels_list.txt DESTINATION model)
```

--------------------------------

### Basic CMake Project Setup

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5/cpp/CMakeLists.txt

Sets the minimum CMake version and project name for the YOLOv5 C++ demo.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_yolov5_demo)
```

--------------------------------

### Include Directories and Installation

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-Det/cpp/CMakeLists.txt

Specifies private include directories for the project and installs the executable and model files. It also installs all .rknn model files found in the model directory.

```cmake
target_include_directories(${PROJECT_NAME} PRIVATE
    ${CMAKE_CURRENT_SOURCE_DIR}
    ${LIBRKNNRT_INCLUDES}
)

install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.jpg DESTINATION model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5_seg/cpp/CMakeLists.txt

Defines the installation rules for the executable, librknnrt, and model files. This ensures that the built application and its assets are correctly placed in the target system.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${LIBRKNNRT} DESTINATION lib)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bus.jpg DESTINATION model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/coco_80_labels_list.txt DESTINATION model)

file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Include Directories and Installation

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov10/cpp/CMakeLists.txt

Sets private include directories for the project and defines installation rules for the executable and associated model files.

```cmake
target_include_directories(${PROJECT_NAME} PRIVATE
    ${CMAKE_CURRENT_SOURCE_DIR}
    ${LIBRKNNRT_INCLUDES}
)

install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bus.jpg DESTINATION model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/coco_80_labels_list.txt DESTINATION model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Include Directories and Installation

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/deeplabv3/cpp/CMakeLists.txt

Specifies private include directories for the target and defines installation rules for the executable and model files. It installs the executable to the root directory and model files to a 'model' subdirectory.

```cmake
target_include_directories(${PROJECT_NAME} PRIVATE
    ${CMAKE_CURRENT_SOURCE_DIR}
    ${LIBRKNNRT_INCLUDES}
)

install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test_image.jpg DESTINATION  model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Installation Rules

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/mobilenet/cpp/CMakeLists.txt

Defines installation rules for the built executable, model assets (images, text, and RKNN model file), ensuring they are placed in the correct destinations.

```cmake
install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/bell.jpg DESTINATION model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/synset.txt DESTINATION model)
set(file_path ${CMAKE_CURRENT_SOURCE_DIR}/../model/mobilenet_v2.rknn)
if (EXISTS ${file_path})
    install(FILES ${file_path} DESTINATION model)
endif()
```

--------------------------------

### Include Directories and Installation

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/mobilesam/cpp/CMakeLists.txt

Specifies private include directories for the project and defines installation rules for the executable, configuration files, and model files.

```cmake
target_include_directories(${PROJECT_NAME} PRIVATE
    ${CMAKE_CURRENT_SOURCE_DIR}
    ${LIBRKNNRT_INCLUDES}
)

install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/coords.txt DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/labels.txt DESTINATION ./model)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/picture.jpg DESTINATION ./model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### YOLOv7 Demo Output Example

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov7/README.md

This is an example of the detection results printed to the console after running the YOLOv7 demo. It includes the detected object label, its bounding box coordinates, and the confidence score.

```text
person @ (212 241 285 511) 0.886
bus @ (86 134 540 444) 0.855
person @ (476 237 561 519) 0.835
person @ (112 234 218 531) 0.835
person @ (79 330 124 524) 0.346
```

--------------------------------

### Project and Dependency Setup

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-Rec/cpp/CMakeLists.txt

Initializes the CMake project and adds subdirectories for external libraries. It also configures OpenCV based on the target system architecture.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_ppocr_rec_demo)

if (ENABLE_ASAN)
	message(STATUS "BUILD WITH ADDRESS SANITIZER")
	set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -fno-omit-frame-pointer -fsanitize=address")
	set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-omit-frame-pointer -fsanitize=address")
	set (CMAKE_LINKER_FLAGS_DEBUG "${CMAKE_LINKER_FLAGS_DEBUG} -fno-omit-frame-pointer -fsanitize=address")
endif ()

add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../../3rdparty/ 3rdparty.out)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../../utils/ utils.out)

#opencv
if(CMAKE_SIZEOF_VOID_P EQUAL 8)
message(STATUS "64bit")
set (TARGET_LIB_ARCH lib64)
else()
message(STATUS "32bit")
set (TARGET_LIB_ARCH lib)
endif()
if (CMAKE_SYSTEM_NAME STREQUAL "Android")
  set(OpenCV_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../../../../3rdparty/opencv/opencv-android-sdk-build/sdk/native/jni/abi-${CMAKE_ANDROID_ARCH_ABI})
elseif(CMAKE_SYSTEM_NAME STREQUAL "Darwin")
  set(OpenCV_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../../../../3rdparty/opencv/opencv-osx-x86_64/share/OpenCV)
elseif(CMAKE_SYSTEM_NAME STREQUAL "Windows")
  set(OpenCV_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../../../../3rdparty/opencv/opencv-windows-x86_64/x64/mingw/staticlib)
else()
    if (TARGET_SOC STREQUAL "x86-64")
      # set(OpenCV_DIR ${MZ_ROOT}/libs/common/opencv/opencv-linux-x86_64/share/OpenCV)
    elseif(TARGET_LIB_ARCH STREQUAL "lib")
      set(OpenCV_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../../../../3rdparty/opencv/opencv-linux-armhf/share/OpenCV)
    else()
      set(OpenCV_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../../../../3rdparty/opencv/opencv-linux-aarch64/share/OpenCV)
    endif()
  endif()
find_package(OpenCV REQUIRED)
message(STATUS OpenCV_DIR=${OpenCV_DIR})
message(STATUS OpenCV_LIBS=${OpenCV_LIBS})

set(CMAKE_INSTALL_RPATH "$ORIGIN/../lib")
```

--------------------------------

### CMakeLists.txt Configuration

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/ppseg/cpp/CMakeLists.txt

This snippet shows the main CMakeLists.txt file for the rknn_ppseg_demo project. It defines the project, includes subdirectories, sets up build targets, links libraries, and configures installation rules.

```cmake
cmake_minimum_required(VERSION 3.10)

project(rknn_ppseg_demo)

if (ENABLE_ASAN)
	message(STATUS "BUILD WITH ADDRESS SANITIZER")
	set (CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -fno-omit-frame-pointer -fsanitize=address")
	set (CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-omit-frame-pointer -fsanitize=address")
	set (CMAKE_LINKER_FLAGS_DEBUG "${CMAKE_LINKER_FLAGS_DEBUG} -fno-omit-frame-pointer -fsanitize=address")
endif ()

add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../3rdparty/ 3rdparty.out)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../utils/ utils.out)

set(CMAKE_INSTALL_RPATH "$ORIGIN/../lib")

if (TARGET_SOC STREQUAL "rk1808" OR TARGET_SOC STREQUAL "rv1109" OR TARGET_SOC STREQUAL "rv1126")
    set(ppseg_file rknpu1/ppseg.cc)
else()
    set(ppseg_file rknpu2/ppseg.cc)
endif ()

file(GLOB SRCS ${CMAKE_CURRENT_SOURCE_DIR}/*.cc)

add_executable(${PROJECT_NAME}
    main.cc
    ${ppseg_file}
)

target_link_libraries(${PROJECT_NAME}
    fileutils
    imageutils
    imagedrawing
    ${LIBRKNNRT}
    dl
)

if (CMAKE_SYSTEM_NAME STREQUAL "Android")
    target_link_libraries(${PROJECT_NAME} log )
endif ()

if (CMAKE_SYSTEM_NAME STREQUAL "Linux")
    set(THREADS_PREFER_PTHREAD_FLAG ON)
    find_package(Threads REQUIRED)
    target_link_libraries(${PROJECT_NAME} Threads::Threads)
endif ()


target_include_directories(${PROJECT_NAME} PRIVATE
    ${CMAKE_CURRENT_SOURCE_DIR}
    ${LIBRKNNRT_INCLUDES}
)

install(TARGETS ${PROJECT_NAME} DESTINATION .)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../model/test.png DESTINATION model)
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Install RKNN Model Files

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_seg/cpp/CMakeLists.txt

Installs all .rknn model files found in the model directory to the 'model' destination.

```cmake
file(GLOB RKNN_FILES "${CMAKE_CURRENT_SOURCE_DIR}/../model/*.rknn")
install(FILES ${RKNN_FILES} DESTINATION model)
```

--------------------------------

### Run PPOCR-Det Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-Det/README.md

Connect to the device via adb, navigate to the demo directory, set the library path, and execute the demo with the model and input image.

```shell
adb shell
cd /userdata/rknn_PPOCR-Det_demo

export LD_LIBRARY_PATH=./lib
./rknn_ppocr_det_demo model/ppocrv4_det.rknn model/test.jpg
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/mms_tts/export_onnx.md

Installs necessary PyTorch and Transformers versions for exporting MMS-TTS models. Ensure compatibility with your environment.

```sh
pip install torch==1.10.0+cpu torchvision==0.11.0+cpu torchaudio==0.10.0 -f https://download.pytorch.org/whl/torch_stable.html

pip install transformers==4.39.3
```

--------------------------------

### Run Wav2Vec2 Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/wav2vec2/README.md

Connect to the device via ADB, navigate to the demo directory, set the LD_LIBRARY_PATH, and execute the Wav2Vec2 demo with the specified model and WAV file.

```shell
adb shell
cd /data/rknn_wav2vec2_demo

export LD_LIBRARY_PATH=./lib
./rknn_wav2vec2_demo model/wav2vec2_base_960h_20s.rknn model/test.wav
```

--------------------------------

### Run PPOCR-Rec Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-Rec/README.md

Connect to the device via adb shell, navigate to the demo directory, set the library path, and execute the recognition demo with the model and test image.

```shell
adb shell
cd /userdata/rknn_PPOCR-Rec_demo

export LD_LIBRARY_PATH=./lib
./rknn_ppocr_rec_demo model/ppocrv4_rec.rknn model/test.png
```

--------------------------------

### Run Yolov6 Demo (Linux)

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov6/README.md

Execute the Yolov6 demo on the device after pushing the files. Ensure the LD_LIBRARY_PATH is set correctly and provide the paths to the model and input image.

```shell
adb shell
cd /userdata/rknn_yolov6_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolov6_demo model/yolov6.rknn model/bus.jpg
```

--------------------------------

### Install Environment for ONNX Export

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yamnet/export_onnx.md

Installs the required Python packages for exporting YAMNet models to ONNX. Ensure you use the specified versions for compatibility.

```shell
pip install onnx==1.16.0
pip install onnxruntime==1.17.3
pip install tensorflow==2.13.1
pip install tensorflow_hub==0.16.1
pip install tf2onnx==1.16.1
```

--------------------------------

### Run RetinaFace Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/RetinaFace/README.md

Connect to the device via adb shell, navigate to the demo directory, set the library path, and execute the RetinaFace demo with model and image paths.

```shell
adb shell
cd /userdata/rknn_RetinaFace_demo

export LD_LIBRARY_PATH=./lib
./rknn_retinaface_demo model/RetinaFace_mobile320.rknn model/test.jpg
```

--------------------------------

### Zipformer Output Example

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/zipformer/README.md

This is an example of the text output from the Zipformer model. Note that results can differ slightly across different platforms, tool versions, and drivers.

```text
Zipformer output: 对我做了介绍那么我想说的是大家如果对我的研究感兴趣呢
```

--------------------------------

### YOLOX Detection Results Example

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolox/README.md

Example output format for the YOLOX detection results, showing detected object labels, their bounding box coordinates, and confidence scores.

```text
bus @ (91 138 549 427) 0.933
person @ (105 234 220 538) 0.901
person @ (210 241 284 506) 0.878
person @ (475 236 560 520) 0.824
person @ (79 327 118 518) 0.508
```

--------------------------------

### Run Yolov5 Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5/README.md

Connect to the device via adb shell, navigate to the demo directory, set the LD_LIBRARY_PATH, and execute the demo with the model and input image. The output image will be saved as out.png.

```shell
adb shell
cd /userdata/rknn_yolov5_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolov5_demo model/yolov5.rknn model/bus.jpg
```

--------------------------------

### YOLOv8 Detection Output Example

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8/README.md

Example of the text output format for YOLOv8 detection results, showing detected object labels, their bounding box coordinates, and confidence scores.

```text
person @ (211 241 283 507) 0.873
person @ (109 235 225 536) 0.866
person @ (476 222 560 521) 0.863
bus @ (99 136 550 456) 0.859
person @ (80 326 116 513) 0.311
```

--------------------------------

### Run YOLOv8 OBB Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_obb/README.md

Connect to the device via adb shell, navigate to the demo directory, set the LD_LIBRARY_PATH, and execute the demo with the model and test image paths.

```shell
adb shell
cd /userdata/rknn_yolov8_obb_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolov8_obb_demo model/yolov8n-obb.rknn model/test.jpg
```

```shell
adb pull /userdata/rknn_yolov8_obb_demo/out.png
```

--------------------------------

### Install OpenCV Manager APK Manually

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/3rdparty/opencv/opencv-android-sdk-build/apk/readme.txt

Use this command to install the OpenCV Manager APK manually via ADB when Google Play is not available. Ensure you replace placeholders with the correct path and version information.

```bash
adb install <path-to-OpenCV-sdk>/apk/OpenCV_<version>_Manager_<app_version>_<platform>.apk
```

--------------------------------

### Run YOLO-World Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolo_world/README.md

Connect to the device via adb shell, navigate to the demo directory, set the LD_LIBRARY_PATH, and execute the demo with the required model and image files.

```shell
adb shell
cd /userdata/rknn_yolo_world_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolo_world_demo clip_text_fp16.rknn model/detect_classes.txt yolo_world_v2s_i8.rknn model/bus.jpg
```

--------------------------------

### YOLOv8 OBB Detection Results Example

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_obb/README.md

This is an example of the text output format for detected objects, including label, bounding box coordinates, and confidence score. Results may vary slightly across different platforms and tool versions.

```text
ship @ (172 757 42 43 angle=0.001677) 0.858
ship @ (582 361 64 62 angle=0.207816) 0.858
ship @ (521 489 37 40 angle=0.067267) 0.858
ship @ (187 627 89 84 angle=0.348365) 0.858
...
ship @ (631 224 15 13 angle=0.404585) 0.599
ship @ (459 96 16 13 angle=0.601354) 0.589
ship @ (482 121 13 11 angle=0.666943) 0.589
ship @ (494 136 18 13 angle=0.741903) 0.500

```

--------------------------------

### YOLOv5 Segmentation Detection Output Example

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5_seg/README.md

This is an example of the text output from a YOLOv5 segmentation model, showing detected objects, their bounding boxes, and confidence scores. Note that results may vary slightly across different platforms and tool versions.

```text
person @ (213 238 284 515) 0.886
person @ (109 241 224 536) 0.861
person @ (474 230 560 522) 0.842
bus @ (98 133 547 461) 0.816
person @ (79 326 124 520) 0.510
```

--------------------------------

### Run PPOCR-System Demo on Linux

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-System/README.md

Execute the PPOCR-System demo on your Linux device. This command sets the library path and runs the demo. If librga.so is not found, you may need to add its location to LD_LIBRARY_PATH.

```shell
adb shell
cd /userdata/rknn_PPOCR-System_demo

export LD_LIBRARY_PATH=./lib
./rknn_ppocr_system_demo ppocrv4_det_i8.rknn ppocrv4_rec_fp16.rknn model/test.jpg
```

```shell
export LD_LIBRARY_PATH=./lib:<LOCATION_LIBRGA>
```

--------------------------------

### Compile and Build YOLOv8 OBB Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_obb/README.md

Navigate to the rknn_model_zoo root directory and execute the build script. Optionally set the GCC_COMPILER path if it's not found.

```shell
# go back to the rknn_model_zoo root directory
cd ../..

# if GCC_COMPILER not found while building, please set GCC_COMPILER path
(optional)export GCC_COMPILER=<GCC_COMPILER_PATH>

./build-linux.sh -t <TARGET_PLATFORM> -a <ARCH> -d yolov8_obb

# such as 
./build-linux.sh -t rk3588 -a aarch64 -d yolov8_obb
```

```shell
export GCC_COMPILER=~/opt/arm-rockchip830-linux-uclibcgnueabihf/bin/arm-rockchip830-linux-uclibcgnueabihf
```

```shell
# Query architecture. For Linux, ['aarch64' or 'armhf'] should shown in log.
adb shell cat /proc/version
```

--------------------------------

### Runtime Path Configuration

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/LPRNet/cpp/CMakeLists.txt

Sets the installation runtime path for shared libraries, ensuring they can be found at runtime.

```cmake
set(CMAKE_INSTALL_RPATH "$ORIGIN/../lib")
```

--------------------------------

### Compile and Build PPOCR-System for Android

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-System/README.md

Use this command to compile and build the PPOCR-System demo for Android. Ensure you set the ANDROID_NDK_PATH and specify the target platform and architecture.

```shell
# go back to the rknn_model_zoo root directory
cd ../../
export ANDROID_NDK_PATH=<android_ndk_path>

./build-android.sh -t <TARGET_PLATFORM> -a <ARCH> -d PPOCR-System

# such as 
./build-android.sh -t rk3588 -a arm64-v8a -d PPOCR-System
```

--------------------------------

### Set GCC_COMPILER Path

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/RetinaFace/README.md

Example of how to set the GCC_COMPILER environment variable if it's not automatically found during the build process.

```shell
export GCC_COMPILER=~/opt/arm-rockchip830-linux-uclibcgnueabihf/bin/arm-rockchip830-linux-uclibcgnueabihf
```

--------------------------------

### Subdirectory and Library Inclusion

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/ppyoloe/cpp/CMakeLists.txt

Includes external subdirectories for third-party libraries and utility modules, and sets the installation runtime path.

```cmake
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../3rdparty/ 3rdparty.out)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../utils/ utils.out)

set(CMAKE_INSTALL_RPATH "$ORIGIN/../lib")
```

--------------------------------

### Push PPOCR-System Demo Files to Linux Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-System/README.md

Transfer the compiled demo files to your Linux device. Use ADB for connected devices or SCP for other boards, pushing to the /userdata/ directory.

```shell
adb push install/<TARGET_PLATFORM>_linux_<ARCH>/rknn_PPOCR-System_demo/ /userdata/
```

--------------------------------

### Run Linux CLIP Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/clip/README.md

Execute the CLIP demo on a Linux device. Navigate to the demo directory and set the library path before running.

```shell
adb shell
cd /userdata/rknn_clip_demo

export LD_LIBRARY_PATH=./lib
./rknn_clip_demo clip_images_fp16.rknn model/dog_224x224.jpg clip_text_fp16.rknn model/text.txt
```

--------------------------------

### Run YOLOv11 Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolo11/README.md

Execute the YOLOv11 demo on the device after pushing the files. Set the LD_LIBRARY_PATH and provide the paths to the model and input image.

```shell
adb shell
cd /userdata/rknn_yolo11_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolo11_demo model/yolo11.rknn model/bus.jpg
```

--------------------------------

### Push Linux Demo Files

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/ppseg/README.md

Push the compiled ppseg demo files to the Linux device. Use scp for other boards if needed.

```shell
adb push install/<TARGET_PLATFORM>_linux_<ARCH>/rknn_ppseg_demo/ /userdata/
```

--------------------------------

### Run YOLOX Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolox/README.md

Execute the YOLOX demo on the device after pushing the files. Set the LD_LIBRARY_PATH and provide the paths to the model and input image.

```shell
adb shell
cd /userdata/rknn_yolox_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolox_demo model/yolox.rknn model/bus.jpg
```

--------------------------------

### Subdirectory and Library Linking

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov10/cpp/CMakeLists.txt

Includes external third-party and utility libraries, sets the installation runtime path, and links essential libraries for the main executable.

```cmake
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../3rdparty/ 3rdparty.out)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../../utils/ utils.out)

set(CMAKE_INSTALL_RPATH "$ORIGIN/../lib")

file(GLOB SRCS ${CMAKE_CURRENT_SOURCE_DIR}/*.cc)

add_executable(${PROJECT_NAME}
    main.cc
    postprocess.cc
    ${rknpu_yolov10_file}
)

target_link_libraries(${PROJECT_NAME}
    imageutils
    fileutils
    imagedrawing    
    ${LIBRKNNRT}
    dl
)
```

--------------------------------

### Run Android Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5_seg/README.md

Execute the YOLOv5-Seg demo on the Android device. Set the LD_LIBRARY_PATH and run the executable with the RKNN model and input image paths. The output is saved as 'out.png'.

```shell
adb shell
cd /data/rknn_yolov5_seg_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolov5_seg_demo model/yolov5_seg.rknn model/bus.jpg
```

--------------------------------

### Run YOLO-World Demo on Android Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolo_world/README.md

Execute the YOLO-World demo on the Android device. This command starts the inference process with specified models and an input image.

```shell
adb shell
cd /data/rknn_yolo_world_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolo_world_demo clip_text_fp16.rknn model/detect_classes.txt yolo_world_v2s_i8.rknn model/bus.jpg
```

--------------------------------

### Compile and Build Wav2Vec2 Demo for Linux

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/wav2vec2/README.md

Navigate to the rknn_model_zoo root directory and execute the build script. Optionally, set the GCC_COMPILER path if it's not found. Specify the target platform, architecture, and the model type 'wav2vec2'.

```shell
# go back to the rknn_model_zoo root directory
cd ../..

# if GCC_COMPILER not found while building, please set GCC_COMPILER path
(optional)export GCC_COMPILER=<GCC_COMPILER_PATH>

./build-linux.sh -t <TARGET_PLATFORM> -a <ARCH> -d wav2vec2

# such as 
./build-linux.sh -t rk3588 -a aarch64 -d wav2vec2
```

--------------------------------

### Compile and Build YOLO-World Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolo_world/README.md

Navigate to the rknn_model_zoo root directory and execute the build script. Set the GCC_COMPILER path if it's not found. Specify the target platform, architecture, and the demo name.

```shell
# go back to the rknn_model_zoo root directory
cd ../../

# if GCC_COMPILER not found while building, please set GCC_COMPILER path
(optional)export GCC_COMPILER=<GCC_COMPILER_PATH>

./build-linux.sh -t <TARGET_PLATFORM> -a <ARCH> -d yolo_world

# such as 
./build-linux.sh -t rk3588 -a aarch64 -d yolo_world
```

--------------------------------

### Run Android PPOCR-Det Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/PPOCR/PPOCR-Det/README.md

Execute the PPOCR-Det demo on the Android device. This command starts the inference process using the specified model and input image.

```shell
adb shell
cd /data/rknn_PPOCR-Det_demo

export LD_LIBRARY_PATH=./lib
./rknn_ppocr_det_demo model/ppocrv4_det.rknn model/test.jpg
```

--------------------------------

### YOLOv11 Detection Result Format

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolo11/README.md

Example output format for the YOLOv11 detection results, showing the detected object class, bounding box coordinates, and confidence score.

```text
person @ (108 236 224 535) 0.898
person @ (212 240 284 509) 0.847
person @ (476 229 559 520) 0.827
person @ (79 358 118 516) 0.396
bus  @ (91 136 554 440) 0.948
```

--------------------------------

### Get Point Coordinates from Image

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/mobilesam/README.md

Use this script to interactively select a point on an image. The script will print the coordinates of the clicked point, which can be used as input for the MobileSAM demo.

```shell
python get_point_coords.py
# Click on the coordinates of a point you need in the image, the point coordinates will be printed.
```

--------------------------------

### Get Box Coordinates from Image

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/mobilesam/README.md

Use this script to interactively select a bounding box on an image by clicking and dragging. The script will output the top-left and bottom-right coordinates of the selected box.

```shell
python get_box_coords.py
# Click on the starting point of the box in the image, then drag the mouse to you need box, the box coordinates: top-left and bottom-right will be printed.
```

--------------------------------

### Compile and Build Android Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5_seg/README.md

Build the Android demo for YOLOv5-Seg. Ensure the ANDROID_NDK_PATH is set and specify the target platform and architecture. Note: RK1808, RV1109, RV1126 do not support Android.

```shell
# go back to the rknn_model_zoo root directory
cd ../../
export ANDROID_NDK_PATH=<android_ndk_path>

./build-android.sh -t <TARGET_PLATFORM> -a <ARCH> -d yolov5_seg
```

```shell
# such as 
./build-android.sh -t rk3588 -a arm64-v8a -d yolov5_seg
```

--------------------------------

### Export ONNX Model with PaddleSeg

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/ppseg/Paddle_2_ONNX.md

Use this command to export your PaddleSeg model to ONNX format. Ensure you have installed the PaddleSeg repository and refer to the deployment documentation for specific configuration details.

```bash
cd PaddleSeg
python deploy/python/infer_onnx_trt.py \
    --config <path to config> \
    --model_path <path to model> \
    --width <img_width> \
    --height <img_height> 
```

--------------------------------

### Compile and Build Linux CLIP Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/clip/README.md

Build the Linux demo for CLIP. Optionally set the GCC_COMPILER path and specify the target platform and architecture.

```shell
# go back to the rknn_model_zoo root directory
cd ../..

# if GCC_COMPILER not found while building, please set GCC_COMPILER path
(optional)export GCC_COMPILER=<GCC_COMPILER_PATH>

./build-linux.sh -t <TARGET_PLATFORM> -a <ARCH> -d clip

# such as 
./build-linux.sh -t rk3588 -a aarch64 -d clip
```

--------------------------------

### Run YOLOv7 Demo on Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov7/README.md

Execute the YOLOv7 demo on the device after pushing the files. Ensure the LD_LIBRARY_PATH is set correctly and provide the paths to the model and input image.

```shell
adb shell
cd /userdata/rknn_yolov7_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolov7_demo model/yolov7.rknn model/bus.jpg
```

--------------------------------

### Executable and Source File Definition

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5_seg/cpp/CMakeLists.txt

Defines the main executable target and dynamically selects source files for post-processing and Yolov5 segmentation based on the target SOC. It also sets the installation runtime path.

```cmake
set(CMAKE_INSTALL_RPATH "$ORIGIN/../lib")

file(GLOB SRCS ${CMAKE_CURRENT_SOURCE_DIR}/*.cc)

#dma
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/../../../3rdparty/allocator/dma)
#drm
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/../../../3rdparty/allocator/drm)

if (TARGET_SOC STREQUAL "rk1808" OR TARGET_SOC STREQUAL "rv1109" OR TARGET_SOC STREQUAL "rv1126")
    set(postprocess_file rknpu1/postprocess.cc)
    set(yolov5_seg_file rknpu1/yolov5_seg.cc)
    #matmul
else()
    set(postprocess_file rknpu2/postprocess.cc)
    set(yolov5_seg_file rknpu2/yolov5_seg.cc)
endif()

add_executable(${PROJECT_NAME}
    main.cc
    ${postprocess_file}
    ${yolov5_seg_file}
)
```

--------------------------------

### Push Android Demo Files to Device

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov5/README.md

Push the compiled YOLOv5 demo files to the Android device using adb.

```shell
adb root
adb remount
adb push install/<TARGET_PLATFORM>_android_<ARCH>/rknn_yolov5_demo/ /data/
```

--------------------------------

### Run YOLOv8-OBB Android Demo

Source: https://github.com/airockchip/rknn_model_zoo/blob/main/examples/yolov8_obb/README.md

Execute the YOLOv8-OBB demo on the Android device. Set the library path and provide the model and test image paths.

```shell
adb shell
cd /data/rknn_yolov8_obb_demo

export LD_LIBRARY_PATH=./lib
./rknn_yolov8_obb_demo model/yolov8n-obb.rknn model/test.jpg
```