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 deepstream5.1 on ubuntu.

The previous article on ubuntu deepstream6.0 may be too demanding for the system version, so I wrote another article on 5.1, which may be more general.

Some versions require:

  • Ubuntu 18.04
  • GStreamer 1.14.1
  • NVIDIA driver 460.32
  • CUDA 11.1
  • TensorRT 7.2.3

1. Install Gstreamer

Sudo apt-get install libgstreamer1.0-0 gstreamer1.0-plugins-good gstreamer1.0-plugins-bad Gstreamer1.0 -plugins-ugly gstreamer1.0-libav gstreamer1.0-doc gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa Gstreamer1.0 -gl gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0- pulseAudio libssl1.0.0 libgstrtspserver-1.0-0 libjansson4Copy the code

Check whether the installation is successful:

dpkg -l | grep gstreamer
Copy the code

Install TensorRT 7.2.3

Download the source code package, download teleport: developer.nvidia.com/compute/mac…

Unzip, put the TensorRT library into the system environment, and then install the TensorRT Python interface:

CD <tensorrt-path>/python PIP install tensorrt-7.2.3.4-cpxx-none-linux_x86_64. WHL CD.. / uff PIP install uff - 0.6.9 - py2. Py3 - none - any. WHLCopy the code

3. Install Librdkafka

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

cd librdkafka/
git reset --hard 7101c2310341ab3f4675fc565f64f0967e135a6a

./configure

sudo make
sudo make install

#The generated library is at /usr/local/lib/librdkafka*
Copy the code

4. Install deepStream SDK

Download the source code package, download teleport: developer.nvidia.com/deepstream-…

Tar -xpvf deepstream_sdk_V5.1.0_x86_64. tbz2 cp -r opt /
#Copy the previous Librdkafka to the DeepStream librarySudo cp -r/usr/local/lib/librdkafka * / opt/nvidia/deepstream/deepstream - 5.1 / lib/CD/opt/nvidia/deepstream/deepstream sudo ./install.shCopy the code

Install the Python interface:

Sudo apt update sudo apt install python3 - gi python3 - dev python3 GST - 1.0 - y - CD/opt/nvidia/deepstream deepstream/lib python3 setup.py installCopy 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

Verify the Python example:

cd /opt/nvidia/deepstream/deepstream/sources
git clone https://github.com/NVIDIA-AI-IOT/deepstream_python_apps
 
#Run Example 1
cd /opt/nvidia/deepstream/deepstream/sources/deepstream_python_apps/apps/deepstream-test1
python3 deepstream_test_1.py /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264 
Copy the code

I have shared with you how to install deepstream5.1 on ubuntu. I hope you found my sharing helpful.

Ubuntu deepStream5.1