DeepStream SDK 5.1
    Highlights:
  • Support for NVIDIA Ampere GPUs with third generation tensor core additions and various performance optimizations
  • Support for audio with a sample application
  • New audio/video template plugin for implementing custom algorithms
  • New sample apps:
    • Standalone smart record application
    • Optical flow and segmentation in python
    • Analytics using region of interest (ROI) and line crossing in Python
    • Audio application to show audio classifier usage
Jetson T4 and A100 (x86)
Operating System Ubuntu 18.04 Ubuntu 18.04
RHEL 8
Dependencies CUDA: 10.2.89
cuDNN: 8.0.0+
TensorRT: 7.1.3
JetPack: 4.5.1
CUDA: 11.1
cuDNN: 8.0.0+
TensorRT: 7.2.2
Driver: R460.32+


Getting Started Resources



Downloads

I Agree To the Terms of the NVIDIA DeepStream SDK 5.1 Software License Agreement

DeepStream 4.0 applications are fully compatible with DeepStream 5.0. Please read the migration guide for more information.

Python Sample Apps & Bindings

Python bindings is now integrated in 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

Blogs & Tutorials

Beginner Friendly Free Self-Paced DLI Online Courses

  • Learn how to build end-to-end intelligent video analytics pipelines using DeepStream and Jetson Nano >> Enroll now
  • Learn how to get started with AI using Jetson Nano >> Enroll now

Webinars




Additional Resources








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.