windows 10 上源码编译OpenCV并支持CUDA | compile opencv with CUDA support on windows 10

最新推荐文章于 2024-07-01 14:23:59 发布

kezunlin

最新推荐文章于 2024-07-01 14:23:59 发布

阅读量846

点赞数

分类专栏： kezunlin.me

本文链接：https://blog.csdn.net/weixin_43654079/article/details/103118702

版权

本文详细介绍了如何在Windows 10上源码编译OpenCV并支持CUDA，包括所需的软件版本、配置步骤和解决可能出现的问题。编译过程涉及CUDA计算能力设置、CPU与GPU性能比较，以及编译和运行时的注意事项。文章还提供了一些示例代码和错误解决方案，帮助读者成功部署和优化OpenCV的GPU性能。

摘要由CSDN通过智能技术生成

本文首发于个人博客https://kezunlin.me/post/6580691f/，欢迎阅读!

compile opencv with CUDA support on windows 10

Series

Guide

requirements:

windows: 10
opencv: 3.1.0
nvidia driver: gtx 1060 382.05 (gtx 970m)
GPU arch(s): sm61 (sm52)
cuda: 8.0
cudnn: 5.0.5
cmake: 3.10.0
vs: vs2015 64

nvidia cuda CC

see cuda compute capacity

笔记本版本的显卡和台式机的计算能力是有差距的。

cuda-enabled nvidia GeForce cc

cpu vs gpu

for opencv functions

speed for cpu and gpu

get source

Get opencv 3.1.0 for git and fix some bugs

    git clone https://github.com/opencv/opencv.git
    cd opencv
    git checkout -b v3.1.0 3.1.0

    # fix bugs for 3.1.0
    git cherry-pick 10896
    git cherry-pick cdb9c
    git cherry-pick 24dbb

    git branch

    master
    * v3.1.0

compile

    mkdir build && cd build && cmake-gui ..

config

configure with VS 2015 win64 with options

    BUILD_SHARED_LIBS  ON
    CMAKE_CONFIGURATION_TYPES Release # Release
    CMAKE_CXX_FLAGS_RELEASE /MD /O2 /Ob2 /DNDEBUG /MP # for multiple processor

    WITH_VTK OFF
    BUILD_PERF_TESTS OFF # if ON, build errors occur

    WITH_CUDA ON
    CUDA_TOOLKIT_ROOT_DIR  C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v8.0
    #CUDA_ARCH_BIN  3.0 3.5 5.0 5.2 6.0 6.1 # very time-consuming 
    CUDA_ARCH_PTX 3.0

for opencv opencv cuda arch

CUDA_ARCH_BIN 3.0 3.5 5.0 5.2 6.0 6.1 relate with

    -gencode;arch=compute_30,code=sm_30;-gencode;arch=compute_35,code=sm_35;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;

CUDA_ARCH_PTX 3.0 relate with

        -gencode;arch=compute_30,code=compute_30;

for caffe caffe cuda arch

the CUDA_ARCH_BIN parameter specifies multiple architectures so as to support a variety of GPU boards. otherwise, cuda programs will not run with other type of GPU boards.

为了支持在多个不同计算能力的GPU上运行可执行程序，opencv/caffe编译过程中需要支持多个不同架构，eg. CUDA_ARCH_BIN 3.0 3.5 5.0 5.2 6.0 6.1, 因此编译过程非常耗时。在编译的而过程中尽可能选择需要发布release版本的GPU架构进行配置编译。

configure and output:

    Selecting Windows SDK version 10.0.14393.0 to target Windows 10.0.17134.
    found IPP (ICV version): 9.0.1 [9.0.1]
    at: C:/compile/opencv/3rdparty/ippicv/unpack/ippicv_win
    CUDA detected: 8.0
    CUDA NVCC target flags: -gencode;arch=compute_30,code=sm_30;-gencode;arch=compute_30,code=compute_30
    Could NOT find Doxy