Get Started with NVIDIA DeepStream SDK
DeepStream is a GStreamer based SDK for creating vision AI applications leveraging AI for image processing and object detection.
DeepStream 6.1.1 Highlights:
DeepStream 6.1 Highlights:
NVIDIA Jetson™: Ubuntu 20.04
NVIDIA Tesla® GPUs (x86): Ubuntu 20.04
Jetson: JetPack: 5.0.2, NVIDIA CUDA®: 11.4, NVIDIA cuDNN: 8.4, NVIDIA TensorRT™: 22.214.171.124 , NVIDIA Triton™ 22.07, GStreamer 1.16.3
Tesla GPUs (x86): Driver: R515+, CUDA: 11.7 Update 1, cuDNN: 8+, TensorRT: 126.96.36.199, Triton 22.07, GStreamer 1.16.3
Note: For JetPack 4.6.1, please use DeepStream 6.0.1. Previous versions of DeepStream can be found here.
To ensure compatibility with supported TensorRT versions , 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 6.1.1
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 Read Me First section of the documentation. For new DeepStream developers or those not reusing old models, this is NOT an issue.
Download DeepStream SDK 6.1.1
DeepStream 5.x applications are fully compatible with DeepStream 6.1. Please read the migration guide for more information.
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.
Introductory DeepStream Webinar
Learn how the latest features of DeepStream are making it easier than ever to achieve real-time performance, even for complex video AI applications.
Find everything you need to start developing your vision AI applications with DeepStream, including documentation, tutorials, and reference applications.
- Applying inference over specific frame regions with NVIDIA DeepStream
- Creating a real-time license plate detection and recognition app
- Developing and deploying your custom action recognition application without any AI expertise using NVIDIA TAO and NVIDIA DeepStream
- Creating a human pose estimation application with NVIDIA DeepStream
- See all DeepStream technical blogs
Webinars and GTC
- How OneCup AI created Betsy, the AI ranch handD: A developer story
- Create intelligent places using NVIDIA pre-trained vision models and DeepStream SDK
- Integrating NVIDIA DeepStream with AWS IoT Greengrass V2 and Sagemaker: Introduction to Amazon Lookout for vision on edge (2022 - Amazon Web Services)
- How Vietnam is tackling traffic congestion with NVIDIA GPUs and DeepStream SDK (2021 - VNPT information technology company)
|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.|