CMakeLists.txt

cmake_minimum_required(VERSION 3.17)
project(autoware_tensorrt_yolov10)

find_package(tensorrt_common)
if(NOT ${tensorrt_common_FOUND})
  message(WARNING "The tensorrt_common package is not found. Please check its dependencies.")
  return()
endif()

find_package(autoware_cmake REQUIRED)
autoware_package()

find_package(OpenCV REQUIRED)

option(CUDA_VERBOSE "Verbose output of CUDA modules" OFF)

# set flags for CUDA availability
option(CUDA_AVAIL "CUDA available" OFF)
find_package(CUDA)
if(CUDA_FOUND)
  find_library(CUBLAS_LIBRARIES cublas HINTS
    ${CUDA_TOOLKIT_ROOT_DIR}/lib64
    ${CUDA_TOOLKIT_ROOT_DIR}/lib
  )
  if(CUDA_VERBOSE)
    message("CUDA is available!")
    message("CUDA Libs: ${CUDA_LIBRARIES}")
    message("CUDA Headers: ${CUDA_INCLUDE_DIRS}")
  endif()
  # Note: cublas_device was depreciated in CUDA version 9.2
  #       https://forums.developer.nvidia.com/t/where-can-i-find-libcublas-device-so-or-libcublas-device-a/67251/4
  #       In LibTorch, CUDA_cublas_device_LIBRARY is used.
  unset(CUDA_cublas_device_LIBRARY CACHE)
  set(CUDA_AVAIL ON)
else()
  message("CUDA NOT FOUND")
  set(CUDA_AVAIL OFF)
endif()

# set flags for TensorRT availability
option(TRT_AVAIL "TensorRT available" OFF)
# try to find the tensorRT modules
find_library(NVINFER nvinfer)
find_library(NVONNXPARSER nvonnxparser)
if(NVINFER AND NVONNXPARSER)
  if(CUDA_VERBOSE)
    message("TensorRT is available!")
    message("NVINFER: ${NVINFER}")
    message("NVONNXPARSER: ${NVONNXPARSER}")
  endif()
  set(TRT_AVAIL ON)
else()
  message("TensorRT is NOT Available")
  set(TRT_AVAIL OFF)
endif()

# set flags for CUDNN availability
option(CUDNN_AVAIL "CUDNN available" OFF)
# try to find the CUDNN module
find_library(CUDNN_LIBRARY
NAMES libcudnn.so${__cudnn_ver_suffix} libcudnn${__cudnn_ver_suffix}.dylib ${__cudnn_lib_win_name}
PATHS $ENV{LD_LIBRARY_PATH} ${__libpath_cudart} ${CUDNN_ROOT_DIR} ${PC_CUDNN_LIBRARY_DIRS} ${CMAKE_INSTALL_PREFIX}
PATH_SUFFIXES lib lib64 bin
DOC "CUDNN library."
)
if(CUDNN_LIBRARY)
  if(CUDA_VERBOSE)
    message(STATUS "CUDNN is available!")
    message(STATUS "CUDNN_LIBRARY: ${CUDNN_LIBRARY}")
  endif()
  set(CUDNN_AVAIL ON)
else()
  message("CUDNN is NOT Available")
  set(CUDNN_AVAIL OFF)
endif()

find_package(OpenMP)
if(OpenMP_FOUND)
  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}")
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
endif()

##########
# tensorrt_yolov10
ament_auto_add_library(${PROJECT_NAME} SHARED
  src/tensorrt_yolov10.cpp
  src/tensorrt_yolov10_node.cpp
)

ament_target_dependencies(${PROJECT_NAME}
  OpenCV
)

if(TRT_AVAIL AND CUDA_AVAIL AND CUDNN_AVAIL)
  # Officially, add_library supports .cu file compilation.
  # However, as of cmake 3.22.1, it seems to fail compilation because compiler flags for
  # C++ are directly passed to nvcc (they are originally space separated
  # but nvcc assume comma separated as argument of `-Xcompiler` option).
  # That is why `cuda_add_library` is used here.
#   cuda_add_library(${PROJECT_NAME}_gpu_preprocess
#     SHARED
#     src/preprocess.cu
#   )

#   target_include_directories(${PROJECT_NAME}_gpu_preprocess PUBLIC
#     $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
#     $<INSTALL_INTERFACE:include/${PROJECT_NAME}>
#   )

#   target_link_libraries(${PROJECT_NAME}
#     ${tensorrt_common_LIBRARIES}
#     ${PROJECT_NAME}_gpu_preprocess
#   )
else()
  target_link_libraries(${PROJECT_NAME}
    ${tensorrt_common_LIBRARIES}
  )
endif()

target_compile_definitions(${PROJECT_NAME} PRIVATE
  TENSORRT_VERSION_MAJOR=${TENSORRT_VERSION_MAJOR}
)

ament_auto_add_library(yolov10_single_image_inference_node SHARED
  src/yolov10_single_image_inference_node.cpp
)

ament_target_dependencies(yolov10_single_image_inference_node
  OpenCV
)

target_link_libraries(yolov10_single_image_inference_node
  ${PROJECT_NAME}
  stdc++fs
)

target_compile_definitions(yolov10_single_image_inference_node PRIVATE
  TENSORRT_VERSION_MAJOR=${TENSORRT_VERSION_MAJOR}
)

rclcpp_components_register_node(yolov10_single_image_inference_node
  PLUGIN "autoware::tensorrt_yolov10::Yolov10SingleImageInferenceNode"
  EXECUTABLE yolov10_single_image_inference
)

ament_auto_add_library(${PROJECT_NAME}_node SHARED
  src/tensorrt_yolov10_node.cpp
)

ament_target_dependencies(${PROJECT_NAME}_node
  OpenCV
)

target_link_libraries(${PROJECT_NAME}_node
  ${PROJECT_NAME}
)

target_compile_definitions(${PROJECT_NAME}_node PRIVATE
  TENSORRT_VERSION_MAJOR=${TENSORRT_VERSION_MAJOR}
)

rclcpp_components_register_node(${PROJECT_NAME}_node
  PLUGIN "autoware::tensorrt_yolov10::TrtYolov10Node"
  EXECUTABLE ${PROJECT_NAME}_node_exe
)

if(BUILD_TESTING)
  find_package(ament_lint_auto REQUIRED)
  ament_lint_auto_find_test_dependencies()
endif()

ament_auto_package(INSTALL_TO_SHARE
  launch
  config
)