NVIDIA DeepStream SDK Developer Guide

DeepStream Getting Started

• Welcome to the DeepStream Documentation
  • NVIDIA DeepStream Overview
• Quickstart Guide
  • Jetson Setup
  • dGPU Setup for Ubuntu
  • dGPU Setup for RedHat Enterprise Linux (RHEL)
  • Running without an X server
  • Platform and OS Compatibility
  • DeepStream Triton Inference Server Usage Guidelines
• Docker Containers
  • A Docker Container for dGPU
  • A Docker Container for Jetson

DeepStream Samples

• C/C++ Sample Apps Source Details
  • Plugin and Library Source Details
• Python Sample Apps Source Details
  • Python Bindings
  • MetaData Access
  • Sample Application Source Details
• DeepStream Reference Application - deepstream-app
  • Application Architecture
  • Reference Application Configuration
  • Configuration Groups
  • Application Tuning for DeepStream SDK
• DeepStream Reference Application - deepstream-test5 app
  • IoT Protocols supported and cloud configuration
  • Message consumer
  • Smart Record - Event based recording
  • OTA model update
• DeepStream Reference Application - deepstream-audio app
• ONNX Parser replace instructions (x86 only)
• DeepStream Reference Application on GitHub
  • Use case applications
  • AI models with DeepStream
  • DeepStream features sample
  • DeepStream ROS
• Sample Configurations and Streams
  • Contents of the package
• Implementing a Custom GStreamer Plugin with OpenCV Integration Example
  • Description of the Sample Plugin: gst-dsexample
  • Enabling and configuring the sample plugin
  • Using the sample plugin in a custom application/pipeline
  • Implementing Custom Logic Within the Sample Plugin
  • Accessing NvBufSurface memory in OpenCV

TAO toolkit Integration with DeepStream

• TAO Toolkit Integration with DeepStream
  • Pre-trained models

Tutorials and How-to's

• NvDCF Parameter Tuning Guide
  • Accuracy-Performance Tradeoffs
  • Visual Feature Types and Feature Sizes
  • Robustness
  • Motion Dynamics
  • Data Association
  • DCF Core Tuning
• Custom YOLO Model in the DeepStream YOLO App
  • How to Use the Custom YOLO Model

DeepStream Performance

• Performance
  • TAO Toolkit Pre-trained models
  • DeepStream reference model and tracker
  • DeepStream reference model
  • Running applications using DLA

DeepStream Custom Model

• Using a Custom Model with DeepStream
  • Custom Model Implementation Interface
  • Custom Output Parsing
  • IPlugin Implementation
  • Input Layer Initialization
  • CUDA Engine Creation for Custom Models
  • IModelParser Interface for Custom Model Parsing

DeepStream Key Features

• Smart Video Record
• IoT
  • Secure Edge-to-Cloud Messaging
  • Bidirectional Messaging
• On the Fly Model Update
  • Assumptions
• NTP Timestamp in DeepStream

DeepStream Application Migration

• Application Migration to DeepStream 5.0 from DeepStream 4.X
  • Major Application Differences with DeepStream 4.X
  • Running DeepStream 4.x compiled Apps in DeepStream 5.0
  • Compiling DeepStream 4.X Apps in DeepStream 5.0

Plugins Development Guide

DeepStream Plugin Guide

• GStreamer Plugin Overview
• MetaData in the DeepStream SDK
  • NvDsBatchMeta: Basic Metadata Structure
  • User/Custom Metadata Addition inside NvDsBatchMeta
  • Adding Custom Meta in Gst Plugins Upstream from Gst-nvstreammux
• Gst-nvinfer
  • Inputs and Outputs
  • Features
  • Gst-nvinfer File Configuration Specifications
  • Gst Properties
  • Tensor Metadata
  • Segmentation Metadata
• Gst-nvinferaudio
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvinferserver
  • Inputs and Outputs
  • Gst-nvinferserver File Configuration Specifications
  • Features
  • Gst Properties
  • Deepstream Triton samples
  • Triton Ensemble Models
  • Tensor Metadata
  • Segmentation Metadata
• Gst-nvtracker
  • Inputs and Outputs
  • Gst Properties
  • Custom Low-Level Library
  • Low-Level Tracker Library Comparisons and Tradeoffs
  • NvDCF Low-Level Tracker
  • IOU Low-Level Tracker
  • KLT Low-Level Tracker
• Gst-nvstreammux
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvstreammux New Alpha
  • Inputs and Outputs
  • Features
  • Gst Properties
  • Mux Config Properties
• Gst-nvstreamdemux
  • Inputs and Outputs
• Gst-nvmultistreamtiler
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvdsosd
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvdsvideotemplate
  • Inputs and Outputs
  • Features
  • Gst Properties
  • Sample pipelines
• Gst-nvdsaudiotemplate
  • Inputs and Outputs
  • Features
  • Gst Properties
  • Sample pipelines
• Gst-nvvideoconvert
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvdewarper
  • Inputs and Outputs
  • Features
  • Configuration File Parameters
  • Gst Properties
• Gst-nvof
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvofvisual
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvsegvisual
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvvideo4linux2
  • Decoder
  • Encoder
• Gst-nvjpegdec
  • Inputs and Outputs
  • Features
  • Gst Properties
• Gst-nvmsgconv
  • Inputs and Outputs
  • Features
  • Gst Properties
  • Schema Customization
  • Payload with Custom Objects
• Gst-nvmsgbroker
  • Inputs and Outputs
  • Features
  • Gst Properties
  • nvds_msgapi: Protocol Adapter Interface
  • nvds_kafka_proto: Kafka Protocol Adapter
  • Azure MQTT Protocol Adapter Libraries
  • AMQP Protocol Adapter
  • REDIS Protocol Adapter
  • nv_msgbroker: Message Broker interface
• Gst-nvdsanalytics
  • Inputs and Outputs
  • Features
  • Gst Properties
  • Configuration File Parameters

Troubleshooting and FAQ Guide

DeepStream Troubleshooting and FAQ

• Troubleshooting
  • You are migrating from DeepStream 4.0+ to DeepStream 5.0
  • “NvDsBatchMeta not found for input buffer” error while running DeepStream pipeline
  • The DeepStream reference application fails to launch, or any plugin fails to load
  • Application fails to run when the neural network is changed
  • The DeepStream application is running slowly (Jetson only)
  • The DeepStream application is running slowly
  • NVIDIA Jetson Nano™, deepstream-segmentation-test starts as expected, but crashes after a few minutes rebooting the system
  • Errors occur when deepstream-app is run with a number of streams greater than 100
  • Errors occur when deepstream-app fails to load plugin Gst-nvinferserver on dGPU only
  • Tensorflow models are running into OOM (Out-Of-Memory) problem
  • Memory usage keeps on increasing when the source is a long duration containerized files(e.g. mp4, mkv)
  • Errors occur when deepstream-app is run with a number of RTSP streams and with NvDCF tracker
  • Troubleshooting in NvDCF Parameter Tuning
• Frequently Asked Questions
  • DeepStream General topics
  • Smart Record
  • Triton

DeepStream API Reference Documentation

DeepStream API Guide

• DeepStream API Guides

DeepStream Legal Information

• DeepStream Legal Information
  • Notice
  • Trademarks
  • Copyright

DeepStream Feedback

• Feedback form
  • Request Documentation Fix