DeepStream Getting Started
- Graph Composer. Assemble complex pipelines using an intuitive and easy-to-use UI and quickly deploy them with Container Builder.
- Action Recognition. Create pipelines to easily identify action in your scene with the new pre-processing plugin. Specify regions of interest and the number of frames you want to process simultaneously.
- Audio-video synchronization for applications such as broadcasting and web conferencing.
- Automatic Speech Recognition (ASR) support. This new plugin performs automatic speech recognition on input audio data and outputs transcribed text.
- Source code for the Python Bindings available on GitHub.com.
- Tracker Updates
- Performance Improvements
- Easy integration of custom trackers.
- New DeepSORT tracker.
- Full REDIS support, previously alpha in version 5.1
- New and updated sample applications available on the SDK and NVIDIA IOT GitHub. Check DeepStream documentation for additional details:
- Action Recognition
- Body Pose Estimation
- Many more.
|Operating System||Ubuntu 18.04|| Ubuntu 18.04|
|Dependencies|| CUDA: 10.2.460 |
| CUDA: 11.4 |
Getting Started Resources
DeepStream 6.0 represents a major release, including significant improvements over the earlier versions. These new features and capabilities take advantage of TensorRT 8, providing best-in-class inference optimization and performance.
To ensure compatibility with TensorRT 8, 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.
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 6.0 for Servers and Workstations
This release supports Tesla T4, V100, and Ampere GPUs.Download .tar Download .deb Get NGC Container for Data Center
DeepStream 6.0 for Jetson
This release supports Jetson TX1, TX2, Nano, NX and AGX Xavier.
Prerequisite: DeepStream SDK 6.0 requires the installation of JetPack 4.6.Download .tar Download .deb Get NGC Container for Edge
Graph Composer 1.0Graph Composer x86 installer (.deb) Graph Runtime for ARM (.deb) Reference examples (.deb)
DeepStream 5.x applications are fully compatible with DeepStream 6.0. 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
- 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
- Building a Real-time Redaction App using NVIDIA DeepStream Part 1 | Part 2
- Bringing Cloud-Native Agility to Edge AI Devices with the NVIDIA Jetson Xavier NX Developer Kit
- 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
- 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
- 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
GTC 2021 November
- GTC 2021:Accelerating the Development of Next-Generation AI Applications with DeepStream 6.0 (Presented by NVIDIA)
- GTC 2021:Bridging the worlds of NVIDIA Metropolis / EGX and Video Management Systems (Presented by Milestone Systems)
- GTC 2021:Building Safer Public Transportation with AI-based Video Analytics (Presented by University of Wollongong)
- GTC 2021: Enabling City-scale AI Video Analytics for Smarter Cities (Presented by SK Telecom)
- GTC 2021: How to Quickly Pilot and Scale Smart Infrastructure Solutions with AI Launchpad and Metropolis (Presented by NVIDIA)
- GTC 2021: How Vietnam is Tackling Traffic Congestion with NVIDIA GPUs and Deepstream SDK (Presented by VNPT Information Technology Company)
- GTC 2021: Intelligent Video Analytics: The brains of the business. (Presented by NVIDIA, Jeb AI, Vertex Studio, Gesta Labs, SVA Tech)
- GTC 2021: The Next Generation of AI-enabled Retail Intra-logistics Solutions. (Presented by NVIDIA, Kinetic Vision, Dematic)
- GTC 2021: Train. Adapt. Optimize. Supercharge your AI Development Workflow and Application Development with NVIDIA TAO Toolkit. (Presented 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.