关于ubuntu:经验分享ubuntu-安装-deepstream60

67次阅读

共计 2595 个字符,预计需要花费 7 分钟才能阅读完成。

欢送关注我的公众号 [极智视界],回复 001 获取 Google 编程标准

O_o>_<   o_OO_o~_~o_O

  本教程具体记录了在 ubuntu 上装置 deepstream6.0 的办法。

  一些版本要求:

  • Ubuntu 18.04
  • GStreamer 1.14.5
  • NVIDIA driver 470.63.01
  • CUDA 11.4
  • TensorRT 8.0.1

1、装置依赖

   装置依赖

sudo apt install libssl1.0.0 libgstreamer1.0-0 gstreamer1.0-tools gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav libgstrtspserver-1.0-0 libjansson4 gcc make git python3

   装置 NVIDIA driver 470.63.01,下载传送:https://www.nvidia.com/Downlo…

chmod 755 NVIDIA-Linux-x86_64-470.63.01.run
sudo ./NVIDIA-Linux-x86_64-470.63.01.run

  装置 CUDA ToolKit 11.4.1 (CUDA 11.4 Update 1),下载传送:https://developer.nvidia.com/…

2、装置 TensorRT 8.0.1

  执行如下命令:

echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 /" | sudo tee /etc/apt/sources.list.d/cuda-repo.list
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
sudo apt-key add 7fa2af80.pub
sudo apt-get update

   下载 TensorRT 8.0.1 GA for Ubuntu 18.04 and CUDA 11.3 DEB local repo package,下载传送:https://developer.nvidia.com/…

   执行如下命令装置 TensorRT 8.0.1:

sudo dpkg -i nv-tensorrt-repo-ubuntu1804-cuda11.3-trt8.0.1.6-ga-20210626_1-1_amd64.deb
sudo apt-key add /var/nv-tensorrt-repo-ubuntu1804-cuda11.3-trt8.0.1.6-ga-20210626/7fa2af80.pub
sudo apt-get update
sudo apt-get install libnvinfer8=8.0.1-1+cuda11.3 libnvinfer-plugin8=8.0.1-1+cuda11.3 libnvparsers8=8.0.1-1+cuda11.3 libnvonnxparsers8=8.0.1-1+cuda11.3 libnvinfer-bin=8.0.1-1+cuda11.3 libnvinfer-dev=8.0.1-1+cuda11.3 libnvinfer-plugin-dev=8.0.1-1+cuda11.3 libnvparsers-dev=8.0.1-1+cuda11.3 libnvonnxparsers-dev=8.0.1-1+cuda11.3 libnvinfer-samples=8.0.1-1+cuda11.3 libnvinfer-doc=8.0.1-1+cuda11.3

3、装置 librdkafka

  clone librdkafka 代码:

git clone https://github.com/edenhill/librdkafka.git

  配置及编译库:

cd librdkafka
git reset --hard 7101c2310341ab3f4675fc565f64f0967e135a6a

./configure
sudo make -j32
sudo make install

   把生成的库拷贝到 deepstream 文件夹:

sudo mkdir -p /opt/nvidia/deepstream/deepstream-6.0/lib
sudo cp /usr/local/lib/librdkafka* /opt/nvidia/deepstream/deepstream-6.0/lib

4、装置 deepstream sdk

4.1 办法一:应用 Debian 装置

  下载 deepstream-6.0_6.0.0-1_amd64.deb Debian 包,下载传送:https://developer.nvidia.com/…

   执行如下命令进行装置:

sudo apt-get install ./deepstream-6.0_6.0.0-1_amd64.deb

4.2 办法二:应用源码装置

  下载 deepstream 源码包,下载传送:https://developer.nvidia.com/…

   解压包并进行编译装置:

sudo tar -xvf deepstream_sdk_v6.0.0_x86_64.tbz2 -C /
cd /opt/nvidia/deepstream/deepstream-6.0/
sudo ./install.sh
sudo ldconfig

4.3 办法三:应用 docker 装置

   这个最简略:

docker pull nvcr.io/nvidia/deepstream:6.0-samples

5、验证是否装置胜利

which deepstream-app

  能定位到 deepstream-app 个别就胜利了,而后能够用 deepstram-app 执行一些 samples,根本命令如下:

deepstream-app -c <path_to_config_file>

   以上分享了在 ubuntu 上装置 deepstream6.0 的办法,心愿我的分享对你会有一点帮忙。


【公众号传送】
《【教训分享】ubuntu 装置 deepstream6.0》

正文完
 0