Get Started With the NVIDIA DeepStream SDK


DeepStream SDK 6.3

Download DeepStream   Forum   Documentation   Try Launchpad

Overview

DeepStream is a GStreamer-based SDK for creating vision AI applications with AI for image processing and object detection. DeepStream 6.3 introduces Graph eXecution Format (GXF), a framework that supports multiple clock domains and brings GPU-accelerated state machines.

Release Highlights


Release notes

DeepStream 6.3 Highlights:

  • New multi-arch containers, including both x86 and NVIDIA Jetson™
  • Four additional plug-ins now available in source-code format
  • Support for MQTT protocol (metadata out)
  • New REST-APIs to control DeepStream pipeline on-the-fly
  • New Google protobuf support
  • DeepStream tracker Re-ID embeddings now available as metadata
  • Multiple video decoder improvements
  • Preprocessing plug-in that adds NVIDIA Triton™ support

GXF and Graph Composer 3.0 Highlights:

  • New Python and C++ APIs
  • Event-triggered data-out support
  • New GXF distributed execution option with UCX support
  • New data formats supported by GXF (Bayer, RAW16, and 3D RGBD)
  • Support for multiple clock sources
  • Remote server for Graph Composer
  • Improvements to Graph Composer sub-graphs

For full details, check the new NGC Collection page and the DeepStream 6.3 Release notes.

Containers

Please note that with the DeepStream 6.3 release, the number and type of available containers has changed. There are three types of containers:

  • Triton: This is a new single container for both x86 and Jetson.
  • Samples: No changes from previous release. One container for X86 and one container for Jetson.
  • Development: This container is x86 only, including Graph Composer.

For full details, check the new NGC Collection page.

Product Advisory

If you’re planning to bring models that use an older version of NVIDIA® TensorRT™ (8.5.2.2), make sure you regenerate the INT8 calibration cache before using them with DeepStream 6.3.


You can find details regarding regenerating the cache in the Read Me First section of the documentation. For new DeepStream developers or those not reusing old models, this step can be omitted.

Download DeepStream SDK 6.3

I Agree To the Terms of the NVIDIA DeepStream SDK 6.3 Software License Agreement to Enable Download Links.

DeepStream 5.x applications are fully compatible with DeepStream 6.3. Please read the migration guide for more information.




Python Bindings

The Python bindings source code and pre-built wheels are now available on GitHub.


Introduction to DeepStream SDK

Quick Start Guide

Get step-by-step instructions for building vision AI pipelines using DeepStream and NVIDIA Jetson or discrete GPUs.


Get Started

Introductory DeepStream Webinar

The next version of DeepStream SDK adds a new graph execution runtime (GXF) that allows developers to build applications requiring tight execution control, advanced scheduling, and critical thread management.


Watch Webinar

Introductory Jetson and Graph Composer Webinar

Learn how NVIDIA DeepStream and Graph Composer make it easier to create vision AI applications for NVIDIA Jetson.


Watch Webinar

Get Started

Find everything you need to start developing your vision AI applications with DeepStream, including documentation, tutorials, and reference applications.

Getting Started with C/C++


Get Started

Getting Started with Python

Learn how the latest features of DeepStream are making it easier than ever to achieve real-time performance, even for complex video AI applications.


Get Started Python Application
GitHub Repository Compile and Install
Python Bindings Python Sample Applications

Getting Started with Graph Composer

Learn how NVIDIA DeepStream and Graph Composer make it easier than ever to create vision AI applications for NVIDIA Jetson.


Get Started



Additional Resources

Technical Blogs

Webinars and GTC

LaunchPad

DLI

Video Tutorial

Forum & FAQ

DeepStream Forums

DeepStream Forum

Tech FAQ

Technical FAQ




Ethical AI
NVIDIA 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. Also, 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.