DeepStream SDK delivers a complete streaming analytics toolkit for real-time AI based video and image understanding and multi-sensor processing. This container is for NVIDIA Jetson platform.
Before You Start
This is the legacy Jetson container page. It hosts DeepStream 9.0 and older containers for Jetson devices. For DeepStream 9.1 or newer, use the consolidated DeepStream container page, which now serves x86, ARM SBSA, DGX Spark, and Jetson from a single location.
Learn about DeepStream Skills. Reusable building blocks for perception, tracking, and reasoning. Paired with DeepStream coding agents, Skills take vision AI development from weeks to hours.
For DeepStream 9.0 and older Jetson containers, see the available tags.
For general Jetson-runtime information (NVIDIA Container Runtime behavior, JetPack version notes, Triton samples setup), see the main DeepStream container page.
Getting Started
This page hosts legacy Jetson containers (DeepStream 9.0 and older). For runtime concepts, prerequisites, and detailed command-line options, see the main DeepStream container page — nothing on that front has changed for older containers.
Prerequisites specific to legacy containers
Each legacy DeepStream version pairs with a specific JetPack. See the available tags page and cross-reference the compatibility matrix on the DeepStream SDK Collection.
Pull
docker pull nvcr.io/nvidia/deepstream-l4t:<legacy-tag>Run
xhost +
docker run -it --rm --runtime=nvidia --network=host -e DISPLAY=$DISPLAY -v /tmp/.X11-unix:/tmp/.X11-unix nvcr.io/nvidia/deepstream-l4t:<legacy-tag>For camera mount arguments, full Docker command-line option details, and general notes, see the main container page's Getting Started section.
Known Limitations
Refer to the release notes for your DeepStream version:
- DeepStream 8.0 and newer: Release notes are hosted as HTML in the DeepStream Developer Guide. Select the version from the pulldown at the top of the page.
- DeepStream 7.1 and earlier: Release notes are hosted as PDFs on the DeepStream documentation archive.
License
/opt/nvidia/deepstream/deepstream-<version>/LicenseAgreement.pdf) as
the authoritative source for the container you are using.
The table below lists the licenses that apply to the latest DeepStream release. Legacy containers may be governed by different terms:
| Asset | Applicable EULA | Notes |
|---|---|---|
| SDK | DeepStream SDK EULA | A copy of the license is available on the following folder of the
SDK: /opt/nvidia/deepstream/deepstream-9.1/LicenseAgreement.pdf |
| Containers | DeepStream NGC License | License grants redistribution rights allowing developers to build applications on top of the DeepStream containers. |
| Development Containers | DeepStream NGC Development License | A development-only license. Does not allow redistribution of the container. |
| TAO Models | NVIDIA AI Product License | All TAO pre-trained models included in the DeepStream SDK are covered by the NVIDIA AI Product License. |
NOTE: By pulling, downloading, or using the DeepStream SDK, you accept the terms and conditions of the EULA licenses listed above.
This project will download and install additional third-party
open-source software projects. Review the license terms of these open
source projects before use.
Please note that all container images come with the following packages
installed:
-
autoconf ( license and license exception )
The software listed below is provided under the terms of GPLv3.
To obtain source code for software provided under licenses that require redistribution of source code, including the GNU General Public License (GPL) and GNU Lesser General Public License (LGPL), available under DeepStream Resources 9.1_3rd_party_oss. This offer is valid for a period of three (3) years from the date of the distribution of this product by NVIDIA CORPORATION.
| Component | License |
|---|---|
| autoconf | GPL 3.0 |
| libtool | GPL 3.0 |
| libglvnd-dev | GPL 3.0 |
| libgl1-mesa-dev | GPL 3.0 |
| libegl1-mesa-dev | GPL 3.0 |
| libgles2-mesa-dev | GPL 3.0 |
Ethical AI
NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.