14 Star 78 Fork 29

PaddlePaddle / FastDeploy

 / 详情

编译失败

已完成
创建于  
2022-11-23 17:35
~/project/paddle/FastDeploy/build$ cmake .. -DENABLE_ORT_BACKEND=ON \
>          -DENABLE_PADDLE_BACKEND=ON \
>          -DENABLE_OPENVINO_BACKEND=ON \
>          -DENABLE_TRT_BACKEND=ON \
>          -DWITH_GPU=ON \
>          -DTRT_DIRECTORY=/Paddle/TensorRT-8.4.1.5 \
>          -DCUDA_DIRECTORY=/usr/local/cuda \
>          -DCMAKE_INSTALL_PREFIX=${PWD}/compiled_fastdeploy_sdk \
>          -DENABLE_VISION=ON \
>          -DENABLE_TEXT=ON
CMake Warning (dev) at CMakeLists.txt:15 (PROJECT):
  Policy CMP0048 is not set: project() command manages VERSION variables.
  Run "cmake --help-policy CMP0048" for policy details.  Use the cmake_policy
  command to set the policy and suppress this warning.

  The following variable(s) would be set to empty:

    CMAKE_PROJECT_VERSION
    CMAKE_PROJECT_VERSION_MAJOR
    CMAKE_PROJECT_VERSION_MINOR
    CMAKE_PROJECT_VERSION_PATCH
This warning is for project developers.  Use -Wno-dev to suppress it.

Decompress file /home/csis/project/paddle/FastDeploy/build/patchelf-0.15.0-x86_64.tar.gz ...
-- Use the default onnxruntime lib. The ONNXRuntime path: /home/csis/project/paddle/FastDeploy/build/third_libs/install/onnxruntime
Decompress file /home/csis/project/paddle/FastDeploy/build/l_openvino_toolkit_centos7_2022.2.0.dev20220829.tgz ...
OPENVINO_LIBS = /home/csis/project/paddle/FastDeploy/build/third_libs/install/openvino/runtime/lib/libopenvino.so
-- CUDA compiler: /usr/local/cuda-11.4/bin/nvcc, version: NVIDIA 11.4.100
Using New Release Strategy - All Arches Packge
-- CUDA detected: 11.4.100
-- NVCC_FLAGS_EXTRA:  -gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=sm_75 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86
-- Copying /Paddle/TensorRT-8.4.1.5/lib to /home/csis/project/paddle/FastDeploy/build/third_libs/install/tensorrt/lib ...
Traceback (most recent call last):
  File "/home/csis/project/paddle/FastDeploy/scripts/copy_directory.py", line 32, in <module>
    copy_directory(sys.argv[1], sys.argv[2])
  File "/home/csis/project/paddle/FastDeploy/scripts/copy_directory.py", line 24, in copy_directory
    raise Exception("Source {} is not exist.".format(src))
Exception: Source /Paddle/TensorRT-8.4.1.5/lib is not exist.
-- result:No such file or directory out:
-- Use the default OpenCV lib from: https://bj.bcebos.com/paddle2onnx/libs/opencv-linux-x64-3.4.16.tgz
Decompress file /home/csis/project/paddle/FastDeploy/build/opencv-linux-x64-3.4.16.tgz ...
FASTTOKENIZER_COMPILE_LIB = /home/csis/project/paddle/FastDeploy/build/third_libs/install/fast_tokenizer/lib/libcore_tokenizers.so
-- 
-- *************FastDeploy Building Summary**********
--   CMake version             : 3.18.6
--   CMake command             : /usr/local/bin/cmake
--   System                    : Linux
--   C++ compiler              : /usr/bin/c++
--   C++ compiler version      : 7.5.0
--   CXX flags                 : -Wno-format
--   Build type                : 
--   Compile definitions       : FASTDEPLOY_LIB;ENABLE_ORT_BACKEND;ENABLE_PADDLE_BACKEND;ENABLE_OPENVINO_BACKEND;WITH_GPU;ENABLE_TRT_BACKEND;ENABLE_VISION;ENABLE_VISION_VISUALIZE;ENABLE_CUDA_PREPROCESS;ENABLE_TEXT;ENABLE_PADDLE_FRONTEND
--   CMAKE_PREFIX_PATH         : 
--   CMAKE_INSTALL_PREFIX      : /home/csis/project/paddle/FastDeploy/build/compiled_fastdeploy_sdk
--   CMAKE_MODULE_PATH         : 
-- 
--   FastDeploy version        : 0.0.0
--   Paddle2ONNX version       : 1.0.3
--   ENABLE_ORT_BACKEND        : ON
--   ENABLE_RKNPU2_BACKEND     : OFF
--   ENABLE_PADDLE_BACKEND     : ON
--   ENABLE_LITE_BACKEND       : OFF
--   ENABLE_POROS_BACKEND      : OFF
--   ENABLE_TRT_BACKEND        : ON
--   ENABLE_OPENVINO_BACKEND   : ON
--   ONNXRuntime version       : 1.12.0
--   Paddle Inference version  : 2.4-dev3
--   OpenVINO version          : 2022.2.0.dev20220829
--   WITH_GPU                  : ON
--   CUDA_DIRECTORY            : /usr/local/cuda
--   TRT_DRECTORY              : /Paddle/TensorRT-8.4.1.5
--   BUILD_CUDA_SRC            : ON
--   ENABLE_VISION             : ON
--   ENABLE_TEXT               : ON
--   ENABLE_DEBUG              : 
--   ENABLE_VISION_VISUALIZE   : 
-- Configuring done
CMake Error: The following variables are used in this project, but they are set to NOTFOUND.
Please set them or make sure they are set and tested correctly in the CMake files:
TRT_INFER_LIB
    linked by target "fastdeploy" in directory /home/csis/project/paddle/FastDeploy
TRT_ONNX_LIB
    linked by target "fastdeploy" in directory /home/csis/project/paddle/FastDeploy
TRT_PLUGIN_LIB
    linked by target "fastdeploy" in directory /home/csis/project/paddle/FastDeploy

-- Generating done
CMake Generate step failed.  Build files cannot be regenerated correctly.

评论 (1)

YiJun 创建了任务
YiJun 任务状态待办的 修改为已完成
YiJun 任务状态已完成 修改为待办的
展开全部操作日志

已解决:下载并设置tensorrt目录就行了

YiJun 任务状态待办的 修改为已完成

登录 后才可以发表评论

状态
负责人
里程碑
Pull Requests
关联的 Pull Requests 被合并后可能会关闭此 issue
分支
开始日期   -   截止日期
-
置顶选项
优先级
参与者(1)
Python
1
https://gitee.com/paddlepaddle/FastDeploy.git
git@gitee.com:paddlepaddle/FastDeploy.git
paddlepaddle
FastDeploy
FastDeploy

搜索帮助

53164aa7 5694891 3bd8fe86 5694891