ubunt20.04安装cuda加速的opencv

环境

RTX3060 Laptop

• 显卡驱动：NVIDIA-SMI 470.256.02 | Driver Version: 470.256.02 | CUDA Version: 11.4
• CUDA:11.4
• CUDNN:8.4.1
• opencv:4.5.3

安装步骤

1. 显卡驱动：

sudo apt update

sudo apt upgrade

添加NVIDIA PPA并安装驱动：

sudo add-apt-repository ppa:graphics-drivers/ppa

sudo apt update

sudo apt install nvidia-driver-470

reboot重启
2. CUDA:
安装时注意取消勾选第一项driver，因为我们已经安装过显卡驱动。
前往官网下载runfile，下载完成后执行sudo sh cuda_11.4.3_470.82.01_linux.run
添加环境变量

echo 'export PATH=/usr/local/cuda-11.4/bin:$PATH' >> ~/.bashrc

echo 'export LD_LIBRARY_PATH=/usr/local/cuda-11.4/lib64:$LD_LIBRARY_PATH' >> ~/.bashrc

source ~/.bashrc

nvcc -V检查一下
3.CUDNN:
官网下载tar包cudnn-linux-x86_64-8.4.1.50_cuda11.6-archive.tar
解压后把对应文件进行拷贝

sudo cp cuda/include/cudnn*.h /usr/local/cuda/include
sudo cp cuda/lib64/libcudnn* /usr/local/cuda/lib64
sudo chmod a+r /usr/local/cuda/include/cudnn*.h /usr/local/cuda/lib64/libcudnn*

4. OPENCV:

• 下载依赖

sudo apt install build-essential cmake git pkg-config libgtk-3-dev libavcodec-dev libavformat-dev libswscale-dev libv4l-dev libxvidcore-dev libx264-dev libjpeg-dev libpng-dev libtiff-dev gfortran openexr libatlas-base-dev python3-dev python3-numpy libtbb2 libtbb-dev libdc1394-22-dev

下载opencv和opencv_contrib并把opencv_contrib放到opencv里

• 预编译 注意路径

cmake \
-D WITH_CUDA=ON \
-D CUDA_ARCH_BIN="8.6" \
-D WITH_CUDNN=ON \
-D OPENCV_DNN_CUDA=ON  \
-D cuDNN_VERSION='8.4' \
-D cuDNN_INCLUDE_DIR='/usr/local/cuda/include' \
-D CUDA_ARCH_PTX="" \
-D OPENCV_EXTRA_MODULES_PATH=/home/strinkin/opencv-4.5.3/opencv_contrib-4.5.3/modules \
-D WITH_GSTREAMER=ON \
-D WITH_LIBV4L=ON  \
-D BUILD_opencv_python3=ON \
-D BUILD_TESTS=OFF \
-D BUILD_PERF_TESTS=OFF \
-D BUILD_EXAMPLES=OFF \
-D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D ENABLE_FAST_MATH=1 \
-D CUDA_FAST_MATH=1 \
-D WITH_CUBLAS=1 \
-D PYTHON3_EXECUTABLE=$(which python3) \
-D PYTHON3_INCLUDE_DIR=$(python3 -c "from distutils.sysconfig import get_python_inc; print(get_python_inc())") \
-D PYTHON3_PACKAGES_PATH=$(python3 -c "from distutils.sysconfig import get_python_lib; print(get_python_lib())") \
-D OPENCV_ENABLE_NONFREE=ON \
-D PYTHON3_NUMPY_INCLUDE_DIRS=/usr/lib/python3/dist-packages/numpy/core/include \
-D PYTHON3_PACKAGES_PATH=/usr/lib/python3/dist-packages \
-D PYTHON_DEFAULT_EXECUTABLE=$(which python3) \
-D OPENCV_PYTHON3_INSTALL_PATH=/usr/lib/python3/dist-packages \
-D BUILD_opencv_python3=ON \
-D BUILD_opencv_python2=OFF \
-D HAVE_opencv_python3=ON \
-D INSTALL_PYTHON_EXAMPLES=ON \
-D INSTALL_C_EXAMPLES=ON \
-D BUILD_opencv_python3=ON \
-D OPENCV_GENERATE_PKGCONFIG=YES \
.. 

• 编译
  nproc查看核心数量
  make -j(核心数量)例如make -j12

• 安装
  sudo make isntall

• 将OpenCV的库添加到路径

sudo gedit /etc/ld.so.conf.d/opencv4.conf 

执行此命令后打开的可能是一个空白的文件，不用管，只需要在文件末尾添加/usr/local/lib
执行sudo ldconfig
编辑sudo gedit /etc/bash.bashrc
在文件最后添加：

PKG_CONFIG_PATH=$PKG_CONFIG_PATH:/usr/local/lib/pkgconfig 
export PKG_CONFIG_PATH 

执行source /etc/bash.bashrc
apt-get install mlocate
sudo updatedb

最后输入pkg-config --modversion opencv4来查看opencv的版本

5. TensorRT

• 官網下載tar包

tar -xvf TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-12.0.tar.gz   #解压
sudo mv TensorRT-8.6.1.6/ /usr/local/

• 添加環境變量

echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/TensorRT-8.6.1.6/lib" >> ~/.bashrc

• 測試

cd /usr/local/TensorRT-8.6.1.6/samples/sampleOnnxMNIST
make
cd /usr/local/TensorRT-8.6.1.6/bin
./sample_onnx_mnist