DeepStream Getting Started

Learn best practices developing DeepStream applications with containers and Visual Studio Code. Watch Now

DeepStream SDK 6.1

Download DeepStream 6.1 here.

DeepStream 6.1 Highlights:

  • Graph Composer UI has a new look and feel (extension type icons, extension metadata search, graph auto-layout, better subgraph UI, and other ease-of-use updates)
  • (Alpha) Graph Composer adds Windows 10 support (with remote execution only)
  • Support for RealSense 400 Series stereo cameras.
  • New post-processing plugin makes it easier to use custom models.
  • Support for NMOS (Networked Media Open Specifications). AI workloads can now be easily integrated with IP-based infrastructures.
  • Integration with NVIDIA Rivermax SDK. Now supports reception and transmission for compressed and uncompressed streams.
  • Support for Unified Communication - X Framework (UCX)/RDMA for data transmission across distributed DeepStream pipelines and nodes (x86/dGPU only).
  • New metadata serialization/deserialization plugins; allows metadata to be embedded within and extracted from encoded video streams (x86/dGPU only).
  • Gst-nvstreammux (new) plugin: Adds audio support and better tuning control enhancements for video conferencing

    • Jetson Tesla GPUs(x86)
    Operating System Ubuntu 20.04 Ubuntu 20.04
    Dependencies JetPack: 5.0.1 DP
    CUDA: 11.4.14
    cuDNN: 8.3.2
    TensorRT: 8.4.0.11 (DP)
    Triton 22.03    		 Driver: R510+
    CUDA: 11.6 Update 1
    cuDNN: 8+
    TensorRT: 8.2.5.1
    Triton 22.03

    Note:

    DeepStream 6.1 for Jetson is compatible with JetPack 5.0.1 Developer Preview only. For JetPack 4.6.1 please use DeepStream 6.0.1. Previous versions of DeepStream can be found here .



    Getting Started Resources


    Product Advisory

    To ensure compatibility with TensorRT versions (as shown in the table on the top of the page), users planning to use models developed with TAO Toolkit (formerly TLT) 3.0-21.08 or earlier MUST re-generate the INT8 calibration cache before using them with DeepStream 6.0 or 6.1.

    Those who are using models and the INT8 calibration cache from previous versions of TensorRT will also need to re-generate the cache.

    You can find details regarding regenerating the cache in the Readme First section of the documentation.

    For new DeepStream developers or those not reusing old models, this is NOT an issue.


    Deep dive into a low-code approach to create real-time vision AI pipelines using Graph Composer. Watch Now

    Downloads

    I Agree To the Terms of the NVIDIA DeepStream SDK 6.1 Software License Agreement

    DeepStream 5.x applications are fully compatible with DeepStream 6.1 . Please read the migration guide for more information.

    Python Sample Apps & Bindings

    The Python bindings source code and pre-built wheels are now available on GitHub. The Bindings build is no longer included with the DeepStream SDK.

    Visit the DeepStream Python Apps Github page for documentation and sample apps.

    Check out the DeepStream SDK technical FAQ for questions commonly asked.

    FAQ

    • Check out the frequently asked questions on DeepStream SDK in the technical FAQ

    Documentation & Forums

    Reference Implementations

    Success Stories

    Blogs & Tutorials

    Beginner Friendly Free Self-Paced DLI Online Courses

    • Building Video AI Applications at the Edge on Jetson Nano >> Enroll now
    • Building Real-Time Video AI Applications >> Enroll now

    Webinars

    GTC



    Additional Resources



      Deep Learning Institute  
      Technical Blogs  
      Developer Forums  




    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.