DeepStream Getting Started
Download DeepStream 6.1 here.
DeepStream 6.1 Highlights:
|Operating System||Ubuntu 20.04||Ubuntu 20.04|
|Dependencies|| JetPack: 5.0.1 DP |
TensorRT: 126.96.36.199 (DP)
| Driver: R510+ |
CUDA: 11.6 Update 1
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
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.
DeepStream 6.1 for Servers and Workstations
This release supports Tesla T4, and Ampere GPUs.Download .tar Download .deb Get NGC Container for Data Center
DeepStream 6.1 for Jetson
This release supports Xavier NX, AGX Xavier and AGX Orin.Download .tar Download .deb Get NGC Container for Edge
Graph Composer 2.0Graph Composer x86 installer (.deb) Reference examples (.deb) Graph Runtime for ARM (.deb) Windows Installer (Alpha) (.exe)
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.
- Check out the frequently asked questions on DeepStream SDK in the technical FAQ
Documentation & Forums
- Release Notes
- Getting Started Guide
- DeepStream Python API
- DeepStream C/C++ API
- Post your questions or feedback in the DeepStream SDK developer forums
- New Reference Applications
- DeepStream NMOS Application
- DeepStream UCX/RDMA Test Applications (UCX Test1, 2 and 3): Examples demonstrate how to send and receive video and audio with and without custom metadata using the UCX framework.
- DeepStream 3D Depth Camera Reference App: Demonstrates how to setup depth capture, depth render, 3D-point-cloud processing and 3D-points rendering pipelines over DS3D interfaces and custom-libs.
- Python DeepStream Test 3: Updated to support Triton inferencing in addition to TRT.
- DeepStream Python Apps: repository contains Python bindings and sample applications
- DeepStream C/C++ Apps: repository contains C/C++ bindings and sample applications
- DeepStream Reference Graph: repository contains Graph Composer sample applications
- DeepStream Pose Estimation: Learn about deploying pose estimation model on DeepStream
- License Plate Recognition using DeepStream: Use license plate detection and recognition pre-trained model for smart city solution
- Add/delete source at RuntimeRuntime source addition/deletion application to show the capability of Deepstream SDK
- DeepStream apps with TAO Toolkit models : This repository provides a DeepStream sample application to run six TAO Toolkit models (DetectNet_v2 / Faster-RCNN / YoloV3 / SSD / DSSD / RetinaNet).
- Using custom YOLO models in DeepStream : The objectDetector_Yolo sample app provides a working example of the open source YOLO models such as YOLOv2, YOLOv3, tiny YOLOv2, and tiny YOLOv3
- Learn how Metropolis development tools are making an impact.
- Learn how Arugga’s AI-powered tomato pollinator gives bees a break.
- Learn how Recycleye AI-driven systems aim to reduce global waste.
- Explore how INEX revolutionizes toll road systems with real-time video processing
- Find out how Nota cuts development time by 50% for real-time traffic control system
- Explore how other top AI teams utilize DeepStream SDK to transform the world around us. Read now
Blogs & Tutorials
- Deploying Models from TensorFlow Model Zoo Using NVIDIA DeepStream and NVIDIA Triton Inference Server
- Video tutorial DeepStream best practices for unlocking greater performance
- How to integrate NVIDIA DeepStream on Jetson Modules with AWS IoT Core and AWS IoT Greengrass
- NVIDIA DeepStream development with Microsoft Azure
- Preparing State-of-the-Art Models for Classification and Object Detection with the NVIDIA TAO Toolkit
- Creating a Real-Time License Plate Detection and Recognition App
- Training with Purpose-built Pre-trained Models Using the NVIDIA TAO Toolkit
- Build and Deploy Accurate Deep Learning Models for Intelligent Image and Video Analytics
DeepStream Turnkey Integration with Cloud Services
AI Training with TAO Toolkit
Perception & Analytics
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
- Create Intelligent Places Using NVIDIA Pre-trained VIsion Models and DeepStream SDK
- Using NVIDIA Pre-trained Models and TAO Toolkit 3.0 to Create Gesture-Based Interactions With A Robot
- Build with DeepStream, deploy and manage with AWS IoT services
- DeepStream edge-to-cloud with Azure IoT
- How To Develop and Optimize Edge AI apps with NVIDIA DeepStream (2022 - NVIDIA)
- Deep Dive Into Jetson and DeepStream (2022 - NVIDIA)
- Smart City
- The Making of Smart Cities (2022 - City of Omaha, City of Las Vegas, California Department of Transportation, City of San Jose, Tel Aviv Municipality)
- Smarter Infrastructure with Digital Twins – NVIDIA Omniverse and Metropolis (2022 - Nota)
- Building Safer Public Transportation with AI-based Video Analytics (2021 - University of Wollongong)
- Enabling City-scale AI Video Analytics for Smarter Cities (2021 - SK Telecom)
- How Vietnam is Tackling Traffic Congestion with NVIDIA GPUs and Deepstream SDK (2021 - VNPT Information Technology Company)
- How AI is Taking on Dirty and Dangerous Jobs (2022 - NVIDIA, Lockheed Martin, KION Group, Sarcos)
- Optimizing Warehouse Logistics Operations with Edge AI and GPU Computing (2022 - ADLINK Technology)
- Scale up Vision AI on private 5G for Industry 4.0 use cases (2022 - Microsoft)
- Developing Effective Inference Models for Autonomous Marine Navigation and Object Detection (2022 - Marine AI, Submergence)
- Measuring Customer Experience in Drive-through Restaurants using NVIDIA Technology (2022 - IKARA Vision Systems)
- The Next Generation of AI-enabled Retail Intra-logistics Solutions (2021 - NVIDIA, Pepsico, Dematic, Kinetic Vision)
- Media & Entertainment
- Cloud Integration
- Integrating NVIDIA DeepStream with AWS IoT Greengrass V2 and Sagemaker: Introduction to Amazon Lookout for Vision on Edge (2022 - Amazon Web Services)
- Simplify Developing and Deploying Intelligent Video Applications (2022 - Microsoft)
- Deployment Ecosystem
- A Platform Approach to Intelligent VSaaS (2022 - Network Optix)
- Bridging the worlds of NVIDIA Metropolis / EGX and Video Management Systems (2021 - Milestone Systems)
- How to Quickly Pilot and Scale Smart Infrastructure Solutions with AI Launchpad and Metropolis (2021 - NVIDIA)
- AI Models Made Simple using NVIDIA TAO (2022 - NVIDIA)
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.