## **Before You Start**

DeepStream 6.1 release builds on top of DeepStream 6.0 momentum bringing new features, a new compute stack and bug fixes. This release includes support for Ubuntu 20.04, GStreamer 1.16, CUDA 11.4, Triton 22.03 and TensorRT 8.4.0.11

If you plan to bring models that were developed on pre 6.1 versions of DeepStream and TAO Toolkit (formerly TLT) you need to re-calibrate the INT8 files so they are compatible with TensorRT 8.4 before you can use them in DeepStream 6.1. Details can be found in the [Readme First](https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_ReadmeFirst.html) section of the SDK Documentation.

## **What is DeepStream?**

NVIDIA’s [DeepStream SDK](https://developer.nvidia.com/deepstream-sdk) delivers a complete streaming analytics toolkit for AI-based multi-sensor processing for video, image, and audio understanding. DeepStream is an integral part of [NVIDIA Metropolis](https://www.nvidia.com/en-us/autonomous-machines/intelligent-video-analytics-platform/), the platform for building end-to-end services and solutions that transform pixels and sensor data into actionable insights. DeepStream SDK features hardware-accelerated building blocks, called plugins, that bring deep neural networks and other complex processing tasks into a processing pipeline. The DeepStream SDK allows you to focus on building optimized Vision AI applications without having to design complete solutions from scratch.

The DeepStream SDK uses AI to perceive pixels and generate metadata while offering integration from the edge-to-the-cloud. The DeepStream SDK can be used to build applications across various use cases including retail analytics, patient monitoring in healthcare facilities, parking management, optical inspection, managing logistics and operations etc.
**DeepStream 6.1 Features**

- Improved Graph Composer development environment. Please note the Graph Composer development environment can work only on x86 systems but the graphs can be deployed on Jetson as well.

- Turnkey integration with the latest [TAO Toolkit](https://developer.nvidia.com/tao-toolkit) AI models. Check the DeepStream documentation for a complete list of supported models.

- Stereo Depth Camera support

- NMOS ( Networked Media Open Specifications) support

- NVIDIA Rivermax integration: Support for transmitting Compressed/Uncompressed streams on Mellanox NIC. It reduces CPU workload and improves PCIe bandwidth by using the kernel bypass mechanism of Rivermax SDK.

- Post processing plugin to support inference post processing

- Develop in Python using DeepStream Python bindings: Bindings are now available in source-code. Download them from [GitHub](https://github.com/NVIDIA-AI-IOT/deepstream_python_apps)

- Updated versions of NVIDIA Compute SDKs: Triton 22.03, TensorRT™ 8.4.0.11 and CUDA® 11.4

- Hardware accelerated video encoding/decoding and image decoding

- Over 30 reference applications in Graph Composer, C/C++, and Python to get you started. Build applications that support: Action Recognition, Pose Estimation and many more. We also include a complete reference app (deepstream-app) that can be setup with intuitive configuration files.

## **DeepStream container for Jetson**

Container support is now available for all Jetson platforms including **Jetson Xavier NX, AGX Xavier and AGX Orin**. The deepstream-l4t:6.1 family of containers are GPU accelerated and based on the NVIDIA Jetson products running on ARM64 architecture.
For additional information refer “[Usage of heavy TRT base dockers since DS 6.1](https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_docker_containers.html#recommended-minimal-l4t-setup-necessary-to-run-the-new-docker-images-on-jetson)” section in NVIDIA DeepStream SDK Developer Guide.

Starting with DeepStream 4.0.1 release, different container variants are being released for **Jetson** (ARM64) platforms to cater to different user needs. Containers are differentiated based on image tags as described below:
- **Base**: The DeepStream base container contains the plugins and libraries that are part of the DeepStream SDK along with dependencies such as CUDA, TensorRT, GStreamer, etc. This image is the recommended one for users that want to create docker images for their own DeepStream based applications. Please note that the base images do not contain sample apps. **(deepstream-l4t:6.1-base)**
- **Samples**: The DeepStream samples container extends the base container to also include sample applications that are included in the DeepStream SDK along with associated config files, models, and streams. This container is ideal to understand and explore the DeepStream SDK using the provided samples. **(deepstream-l4t:6.1-samples)**
- **IoT**: The DeepStream IoT container extends the base container to include the DeepStream test5 application along with associated configs and models. This container can be used to enable multi-stream DeepStream applications that can be integrated with the various messaging backends including Kafka, Azure IoT, REDIS,  and MQTT thereby enabling IoT use cases. **(deepstream-l4t:6.1-iot)**
- **Deployment with Triton**: The DeepStream Triton container enables running inference using [Triton Inference server](https://developer.nvidia.com/nvidia-triton-inference-server). With this, developers can run inference natively using TensorFlow, TensorFlow-TensorRT and ONNX-RT. Inference with Triton is supported in the reference application (deepstream-app). To  build deepstream reference applications in the container refer steps mentioned in section “[Building DeepStream reference application source inside L4T triton container](https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_docker_containers.html#building-deepstream-reference-application-source-inside-l4t-triton-container)” in NVIDIA DeepStream SDK Developer Guide. Note: Applications that may depend on opencv4 will not compile as opencv4 is not packaged within this container. To learn more about how to use Triton with DeepStream, refer to the Plugin guide in DeepStream 6.1 documentation (Gst-nvinferserver). **(deepstream-l4t:6.1-triton)**

These containers leverage the [NVIDIA Container Runtime on Jetson](https://github.com/NVIDIA/nvidia-docker/wiki/NVIDIA-Container-Runtime-on-Jetson), which is available for install as part of [NVIDIA JetPack version 5.0.1 DP](https://developer.nvidia.com/embedded/jetpack) . The platform specific libraries and select device nodes for a particular device are mounted by the NVIDIA Container Runtime into the DeepStream container from the underlying host, thereby providing necessary dependencies (BSP Libraries) for DeepStream applications to execute within the container.

Since Jetpack 5.0.1 DP, NVIDIA Container Runtime no longer mounts user level libraries like CUDA, cuDNN and TensorRT from the host. These will instead be installed inside the containers.

## Dockers from previous release Cuda update

DeepStream dockers or dockers derived from previous releases (before DS 6.1) will need to update their Cuda GPG key to perform software updates. Please see [link](https://forums.developer.nvidia.com/t/notice-cuda-linux-repository-key-rotation/212772) for details.

## **Known Issues**

VPI version in the Jetson Dockers is version 2.0.13.  The one installed by Jetpack 5.0.1 DP is VPI 2.0.14. There is no difference in DS related functionalities.

The DS Containers (base, samples, iot, triton) Security scans for this container image outside of NGC may show CVE-2022-1015 as being present in the container image. When [CVE-2022-1015](https://ubuntu.com/security/CVE-2022-1015) is flagged, it is a vulnerability in the host kernel and the container image has header files that reflect such a kernel.  It is recommended to ensure the host kernel is updated with the latest vulnerability patches when executing container content.

## **Running DeepStream**

### Prerequisites

Ensure these prerequisites are available on your system:

1. Jetson device running L4T BSP r34.1.1

2. JetPack 5.0.1 DP

### Pull the container

Before running the container, use docker pull to ensure an up-to-date image is installed. Once the pull is complete, you can run the container image.

Procedure

1. In the Pull column, click the icon to copy the docker pull command for the deepstream container.

2. Open a command prompt and paste the pull command. The pulling of the container image begins. Ensure the pull completes successfully before proceeding to the next step.

### Run the container

To run the container:

1. Allow external applications to connect to the host's X display:

~~~~
xhost +
~~~~

2. Run the docker container using the nvidia-docker (use the desired container tag in the command line below):

~~~~
sudo docker run -it --rm --net=host --runtime nvidia  -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-6.1 -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/deepstream-l4t:6.1-base
~~~~

**Command line options explained:**

- -it means run in interactive mode

- --rm will delete the container when finished

- -v is the mounting directory, and used to mount host's X11 display in the container filesystem

- Users can mount additional directories (using -v option) as required to easily access configuration files, models, and other resources. (i.e., use -v  /home:/home to mount the home directory into the container filesystem.

- Additionally, *--cap-add SYSLOG* option needs to be included to enable usage of the nvds_logger functionality inside the container.

See /opt/nvidia/deepstream/deepstream-6.1/README inside the container for deepstream-app usage information.
Additional argument to add to above docker command for accessing CSI Camera from Docker:
-v /tmp/argus_socket:/tmp/argus_socket
For USB Camera additional argument
--device /dev/video<v4l2 node id>

## Limitations

The NVIDIA Container Runtime available in JetPack 5.0.1 DP. Please see the list below for limitations in the current enablement of DeepStream for Jetson containers.

Supports deployment only: The DeepStream container for Jetson is intended to be a deployment container and is not set up for building sources. Please refer “Docker Containers” Section within the DeepStream 6.1 Plugin Guide Section for instructions on how to build custom containers based on DeepStream from either Jetson device or your workstation

AMQP support is not included inside the container. Please refer “AMQP Protocol Adapter” Section within the DeepStream 6.1 Plugin Guide Section for instructions on how to install necessary dependencies for enabling AMQP if required

There are known bugs and limitations in the SDK. To learn more about those, refer to the [release notes](https://docs.nvidia.com/metropolis/deepstream/DeepStream_6.1_Release_Notes.pdf)

## License

-All Jetson containers are released under [NVIDIA License Agreement](https://developer.nvidia.com/deepstream-eula-ngc)

A copy of the license can also be found within a specific container at the following location: `/opt/nvidia/deepstream/deepstream-6.1/LicenseAgreement.pdf`. By pulling and using the DeepStream SDK (deepstream) container from NGC, you accept the terms and conditions of this license.

Please note that all container images come with the following packages installed:
[librdkafka](https://github.com/edenhill/librdkafka/blob/7101c2310341ab3f4675fc565f64f0967e135a6a/LICENSE), [hiredis](https://github.com/redis/hiredis/blob/d5b4c69b7113213c1da3a0ccbfd1ee1b40443c7a/COPYING).

### Technical blogs

- Read the technical tutorial on how [PeopleNet model can be trained with custom data using by TAO Toolkit (earlier NVIDIA Transfer Learning Toolkit.)](https://devblogs.nvidia.com/training-custom-pretrained-models-using-tlt/)

## Suggested Reading

- DeepStream documentation containing development guide, getting started, plug-ins manual, API reference manual, migration guide, technical FAQ and release notes can be found at [Getting Started with DeepStream page](https://developer.nvidia.com/deepstream-getting-started)

- If you have any questions or feedback, please refer to the discussions on [DeepStream 6.1 Forums](https://forums.developer.nvidia.com/c/accelerated-computing/intelligent-video-analytics/deepstream-sdk/15).

- The DeepStream SDK is also available as a Debian package (.deb) or tar file (.tbz2) [at NVIDIA Developer Zone](https://developer.nvidia.com/deepstream-getting-started)

- For more information, including blogs and webinars, see the [DeepStream SDK website](https://developer.nvidia.com/deepstream-sdk).

- Download [TAO Toolkit from NGC](https://ngc.nvidia.com/catalog/containers/nvidia:tlt-streamanalytics)

#### 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.

deepstream-l4t

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.

DeepStream-l4t

Description

Publisher

Latest Tag

Modified

Compressed Size

Multinode Support

Multi-Arch Support

6.1-triton (Latest) Scan Results