Welcome to follow my public account [Jizhi Vision], reply 001 to get Google programming specification

O_o >_< O_o O_o ~_~ O_o

This tutorial details how to install deepstream6.0 on ubuntu.

Some versions require:

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

1. Install dependencies

Install dependencies

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 python3Copy the code

Install NVIDIA driver 470.63.01, download teleport: www.nvidia.com/Download/dr…

Run sudo./ nvidia-linux-x86_64-470.63.01.runCopy the code

Install the CUDA ToolKit 11.4.1 (CUDA 11.4 Update 1), download the teleport: developer.nvidia.com/cuda-11-4-1…

Install TensorRT 8.0.1

Run the following command:

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
Copy the code

Download TensorRT 8.0.1 GA for Ubuntu 18.04 and 11.3 DEB CUDA local repo package, download the teleport: developer.nvidia.com/compute/mac…

Run the following command to install 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 = + cuda11.3 8.0.1-1 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 + cuda11.3Copy the code

3. Install Librdkafka

Clone Librdkafka

git clone https://github.com/edenhill/librdkafka.git
Copy the code

Configure and compile libraries:

cd librdkafka
git reset --hard 7101c2310341ab3f4675fc565f64f0967e135a6a

./configure
sudo make -j32
sudo make install
Copy the code

Copy the generated library to the deepStream folder:

Sudo mkdir -p/opt/nvidia/deepstream deepstream - 6.0 / lib/sudo cp/usr/local/lib/librdkafka * / opt/nvidia/deepstream/deepstream - 6.0 / libCopy the code

4. Install deepStream SDK

4.1 Method 1: Install using Debian

Download deepstream – 6.0 _6. 0.0 1 _amd64. Deb Debian package, download the teleport: developer.nvidia.com/deepstream-…

Run the following command to install:

Sudo apt - get the install. / deepstream - 6.0 _6. 0.0 1 _amd64. DebCopy the code

4.2 Method 2: Install it using source code

Download deepstream source package, download teleport: developer.nvidia.com/deepstream_…

Unzip the package and compile and install:

Sudo tar - XVF deepstream_sdk_v6. 0.0 _x86_64. Tbz2 - C/CD/opt/nvidia/deepstream deepstream - 6.0 / sudo. / install. Sh sudo ldconfigCopy the code

4.3 Method 3: Use Docker installation

This is the easiest:

Docker pull NVCR. IO/nvidia/deepstream: 6.0 samplesCopy the code

5. Verify that the installation is successful

which deepstream-app
Copy the code

It’s usually successful if you can locate deepstream-app, and then you can run some samples with deepstram-app. The basic command is as follows:

deepstream-app -c <path_to_config_file>
Copy the code


I have shared the methods for installing deepstream6.0 on ubuntu. I hope you found my sharing helpful.

[详 细 介 绍] Ubuntu DeepStream6.0