依照项目部署命令 <div class="highlight highlight-source-cmake notranslate position-relativ

重新编译一下库，编译案例的时候输出ite.ai.toolkit_LIBS_DIRS： <div class="highlight highlight-source-

感谢，模型已经成功加载并计算完成。提几个点：模型和图片地址根据需要修改 <div class="hi

[BUG]libopencv_imgproc.so.409: cannot open shared object file: No such file or directory about lite.ai.toolkit HOT 4 OPEN

Flamse commented on May 28, 2024

[BUG]libopencv_imgproc.so.409: cannot open shared object file: No such file or directory

from lite.ai.toolkit.

Comments (4)

DefTruth commented on May 28, 2024

需要在可执行文件目录下，export LD_LIBRARY_PATH=$PWD:$LD_LIBRARY_PATH

from lite.ai.toolkit.

DefTruth commented on May 28, 2024

重新编译一下库，编译案例的时候输出ite.ai.toolkit_LIBS_DIRS：

cmake_minimum_required(VERSION 3.10)
project(lite_yolov5)
set(CMAKE_CXX_STANDARD 17)

set(lite.ai.toolkit_DIR YOUR-PATH-TO/lite.ai.toolkit/build/install)
find_package(lite.ai.toolkit REQUIRED PATHS ${lite.ai.toolkit_DIR})
if (lite.ai.toolkit_Found)
    message(STATUS "lite.ai.toolkit_INCLUDE_DIRS: ${lite.ai.toolkit_INCLUDE_DIRS}")
    message(STATUS "        lite.ai.toolkit_LIBS: ${lite.ai.toolkit_LIBS}")
    message(STATUS "   lite.ai.toolkit_LIBS_DIRS: ${lite.ai.toolkit_LIBS_DIRS}")
endif()
add_executable(lite_yolov5 test_lite_yolov5.cpp)
target_link_libraries(lite_yolov5 ${lite.ai.toolkit_LIBS})

然后把相关的路径export一下即可

from lite.ai.toolkit.

Flamse commented on May 28, 2024

感谢，模型已经成功加载并计算完成。提几个点：

模型和图片地址根据需要修改

  std::string onnx_path = "../../../../examples/hub/onnx/cv/yolov5s.onnx";
  // ...

项目对模型输入做了规范，下载项目给出的模型可以完成测试，其他资源处下载的模型可以使用Python对onnx模型文件的输入格式进行修改

terminate called after throwing an instance of 'Ort::Exception'
  what():  Unexpected input data type. Actual: (tensor(float)) , expected: (tensor(float16))