笔记--Ubuntu18.04安装Deepstream 6.0

目录

1-- 安装依赖

2-- 安装Cuda Toolkit 11.4.1

3-- 安装cudnn 8.2+

4-- 安装TensorRT 8.0.1

5-- 安装librdkafka

6-- 安装 deepstream sdk

7-- 验证与测试

8-- 问题记录

参考

---

1-- 安装依赖

① 改换系统源为阿里云 （部分packages在系统默认源中不存在）

执行以下命令：

vi /etc/apt/sources.list

替换为以下内容：

deb http://mirrors.aliyun.com/ubuntu/ bionic main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ bionic main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ bionic-security main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ bionic-security main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ bionic-updates main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ bionic-updates main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ bionic-backports main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ bionic-backports main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ bionic-proposed main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ bionic-proposed main restricted universe multiverse

更新

sudo apt-get update # 更新软件列表
apt-get upgrade # 更新安装包

② 安装依赖

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

2-- 安装Cuda Toolkit 11.4.1

wget https://developer.download.nvidia.com/compute/cuda/11.4.1/local_installers/cuda_11.4.1_470.57.02_linux.run
sudo sh cuda_11.4.1_470.57.02_linux.run

3-- 安装cudnn 8.2+

# 下载网址：https://developer.nvidia.com/rdp/cudnn-archive

# 安装参考：https://blog.csdn.net/weixin_43863869/article/details/124398784?spm=1001.2014.3001.5502

4-- 安装TensorRT 8.0.1

① 第一步

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  

运行 sudo apt-get update 这步可能会报公钥无效，可通过 sudo apt-key adv --keyserver keyserver.ubuntu.com --recv-keys A4B469963BF863CC 解决 （A4B469963BF863CC表示无效的公钥）

② 下载Tensor RT Package

# 下载地址：Tensor RT8.01下载地址

③ 安装 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

④ 测试是否安装成功

dpkg -l | grep TensorRT

5-- 安装librdkafka

① 拷贝源码

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

② 编译安装

cd librdkafka
git reset --hard 7101c2310341ab3f4675fc565f64f0967e135a6a

./configure
sudo make -j32
sudo make install

③ 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

6-- 安装 deepstream sdk

① 使用deb安装

# 下载地址：deepstream sdk deb包下载地址

② 安装

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

7-- 验证与测试

① 定位

which deepstream-app

② 运行examples 

export LIBGL_DRIVERS_PATH=/usr/lib/x86_64-linux-gnu/dri
export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/  

# export的作用是解决以下错误：libEGL warning: MESA-LOADER: failed to open swrast (search paths LIBGL_DRIVERS_PATH=/usr/lib/x86_64-linux-gnu/dri)

cd /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app
ls
deepstream-app -c /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt

8-- 问题记录

① 可能需要额外安装的依赖：

sudo apt-get install mesa-utils
sudo apt-get install mesa-libGLw.x86_64
sudo apt-get install -y mesa-libGLw-devel.x86_64
sudo apt-get install mesa-dri-drivers

② 使用配置文件source30_1080p_dec_infer-resnet_tiled_display_int8.txt时，会报错：

 可将[sink0]的enable改为0或者type改为1，采用FakeSink测试。

③采用原配置文件source30_1080p_dec_infer-resnet_tiled_display_int8.txt测试时，出现闪退的情况，以及报错：Segmentation fault (core dumped)。之前已有相应的问题，见链接，现象描述，但未解决。

④目前，使用上述方法无法看到窗口视频情况（会闪退），使用FakeSink可以顺利运行，运行结果如下图，若能解决上面出现的问题，恳请留言或者私信告知博主，万分感谢！

参考

安装依赖

公钥报错

Ubuntu 安装 deepstream6.0