Logo
6.0.1 Release

DeepStream Getting Started

  • Welcome to the DeepStream Documentation
    • NVIDIA DeepStream Overview
      • DeepStream Graph Architecture
      • DeepStream reference app
      • Getting started with building apps
      • DeepStream in Python
  • Readme First
    • Additional Resources
      • Documentation
      • Forums
  • Quickstart Guide
    • Jetson Setup
      • Install Jetson SDK components
      • Install Dependencies
        • Install librdkafka (to enable Kafka protocol adaptor for message broker)
      • Update BSP library
      • Install the DeepStream SDK
      • Run deepstream-app (the reference application)
        • Boost the clocks
      • Run precompiled sample applications
    • dGPU Setup for Ubuntu
      • Remove all previous DeepStream installations
      • Install Dependencies
        • Install NVIDIA driver 470.63.01
        • Install CUDA Toolkit 11.4.1 (CUDA 11.4 Update 1)
        • Install TensorRT 8.0.1
        • Install librdkafka (to enable Kafka protocol adaptor for message broker)
      • Install the DeepStream SDK
      • Run the deepstream-app (the reference application)
      • Run precompiled sample applications
    • dGPU Setup for RedHat Enterprise Linux (RHEL)
      • Remove all previous DeepStream installations
      • Install Dependencies
        • Install NVIDIA driver 470.63.01
        • Install CUDA Toolkit 11.4 (CUDA 11.4 Update 1)
        • Install TensorRT 8.0.1
        • Install librdkafka (to enable Kafka protocol adaptor for message broker)
      • Install the DeepStream SDK
      • Run the deepstream-app (the reference application)
      • Run precompiled sample applications
    • Running without an X server
    • Platform and OS Compatibility
    • DeepStream Triton Inference Server Usage Guidelines
      • dGPU
      • Jetson
    • Using DLA for inference
      • Separate processes
      • Single process
  • Docker Containers
    • A Docker Container for dGPU
    • A Docker Container for Jetson
    • Creating custom DeepStream docker for dGPU using DeepStreamSDK package
    • Creating custom DeepStream docker for Jetson using DeepStreamSDK package

DeepStream Samples

  • C/C++ Sample Apps Source Details
    • Plugin and Library Source Details
  • Python Sample Apps and Bindings Source Details
    • Sample Application Source Details
    • Python Bindings and Application Development
      • Prerequisites
      • Running Sample Applications
      • Pipeline Construction
    • MetaData Access
      • Memory Management
      • Allocations
      • String Access
        • Setting String Fields
        • Reading String Fields
      • Casting
      • Callback Function Registration
      • Optimizations and Utilities
      • Image Data Access
  • DeepStream Reference Application - deepstream-app
    • Application Architecture
    • Reference Application Configuration
      • Expected Output for the DeepStream Reference Application (deepstream-app)
    • Configuration Groups
      • Application Group
      • Tiled-display Group
      • Source Group
      • Streammux Group
      • Preprocess Group
      • Primary GIE and Secondary GIE Group
      • Tracker Group
      • Message Converter Group
      • Message Consumer Group
      • OSD Group
      • Sink Group
      • Tests Group
      • NvDs-analytics Group
    • Application Tuning for DeepStream SDK
      • Performance Optimization
        • DeepStream best practices
        • Jetson optimization
        • Triton
        • Inference Throughput
      • Reducing Spurious Detections
  • DeepStream Reference Application - deepstream-test5 app
    • IoT Protocols supported and cloud configuration
    • Message consumer
    • Smart Record - Event based recording
    • OTA model update
      • Using the OTA functionality
  • DeepStream Reference Application - deepstream-audio app
    • DeepStream Audio Reference Application Architecture and Sample Graphs
  • DeepStream Reference Application on GitHub
    • Use case applications
    • AI models with DeepStream
    • DeepStream features sample
  • Sample Configurations and Streams
    • Contents of the package
      • Scripts included along with package
  • Implementing a Custom GStreamer Plugin with OpenCV Integration Example
    • Description of the Sample Plugin: gst-dsexample
      • GstBaseTransfrom Class Functions
      • Other supporting functions
    • Enabling and configuring the sample plugin
    • Using the sample plugin in a custom application/pipeline
    • Implementing Custom Logic Within the Sample Plugin
    • Adding NVTX APIs for 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

  • Custom YOLO Model in the DeepStream YOLO App
    • How to Use the Custom YOLO Model
      • Set up the sample
  • NvMultiObjectTracker Parameter Tuning Guide
    • Accuracy-Performance Tradeoffs
      • Visual Feature Types and Feature Sizes
      • Detection Interval
      • Video Frame Size for Tracker
    • Robustness
      • Target Creation Policy
      • Target Termination Policy
    • State Estimation
      • Kalman Filter
    • Data Association
    • DCF Core Tuning
      • DCF Filter Learning

DeepStream Performance

  • Performance
    • TAO Pre-trained models
    • DeepStream reference model and tracker
    • Configuration File Settings for Performance Measurement
    • DeepStream reference model
      • Data center GPU - GA100
        • System Configuration
        • Application Configuration
      • Data center GPU - T4
        • System Configuration
        • Application Configuration
      • Jetson
        • System Configuration
        • Jetson Nano
        • Jetson AGX Xavier
        • Jetson NX
        • Jetson TX2
        • Jetson TX1

DeepStream Custom Model

  • Using a Custom Model with DeepStream
    • Custom Model Implementation Interface
    • Custom Output Parsing
    • IPlugin Implementation
      • How to Use IPluginCreator
      • How to Use IPluginFactory
        • For Caffe Files
        • For Uff Files
        • During Deserialization
    • Input Layer Initialization
    • CUDA Engine Creation for Custom Models
    • IModelParser Interface for Custom Model Parsing

DeepStream Key Features

  • Smart Video Record
    • Smart Video Record Module APIs
    • Smart Video Record Configurations
  • IoT
    • Secure Edge-to-Cloud Messaging
      • 2-way TLS Authentication
        • Overview of Steps
        • TLS Version
        • Key generation
        • Certificate Signing
        • Choice of Cipher
        • Configure TLS options in Kafka config file for DeepStream
      • SASL/Plain
        • Overview of Steps
        • TLS Configuration
        • Credential Storage
        • Choosing Between 2-way TLS and SASL/Plain
      • Impact on performance
    • Bidirectional Messaging
      • Edge-to-Cloud
      • Cloud-to-Edge
      • NvMsgbroker Library
    • Autoreconnect feature
  • On the Fly Model Update
    • Assumptions
  • NTP Timestamp in DeepStream
  • AV Sync in DeepStream
    • Setup for RTMP/RTSP Input streams for testing
      • RTMP Server Setup
        • Command to simulate 2 RTMP streams using ffmpeg
      • RTSP Server Setup
    • AVSync Reference Pipelines
      • Pipelines with existing nvstreammux component
        • RTMP_IN -> RTMP_OUT
        • FILE_IN->RTSP_OUT
        • FILE_IN->RTMP_OUT
        • RTMP_IN->FILE_OUT
        • RTSP_IN->FILE_OUT
        • FILE_IN->FILE_OUT
        • RTSP_IN->RTSP_OUT
        • RTMP_IN->RTSP_OUT
      • Reference AVSync + ASR (Automatic Speech Recognition) Pipelines with existing nvstreammux
        • RTMP_IN->RTMP_OUT
        • RTSP_IN->RTMP_OUT
        • FILE_IN->RTMP_OUT
      • Pipelines with New nvstreammux component
        • RTMP_IN->RTMP_OUT
        • RTSP_IN->RTMP_OUT
        • FILE_IN->RTSP_OUT
        • FILE_IN->RTMP_OUT
        • RTMP_IN->FILE_OUT
        • RTSP_IN->FILE_OUT
        • FILE_IN->FILE_OUT
        • RTSP_IN->RTSP_OUT
        • RTMP_IN->RTSP_OUT
      • Reference AVSync + ASR Pipelines (with new nvstreammux)
        • RTMP_IN->RTMP_OUT
        • RTSP_IN->RTMP_OUT
        • FILE_IN->RTMP_OUT
      • Gst-pipeline with audiomuxer (single source, without ASR + new nvstreammux)
        • RTMP_IN->FILE_OUT
  • DeepStream 3D Action Recognition App
    • Getting Started
      • Prerequisites
      • Run 3D Action Recognition Examples
      • Run 2D Action Recognition Examples
    • DeepStream 3D Action Recognition App Configuration Specifications
      • deepstream-3d-action-recognition [action-recognition] group settings
      • Custom sequence preprocess lib user settings [user-configs] for gst-nvdspreprocess
      • Custom lib and `gst-nvdspreprocess` Settings for Action Recognition
    • Build Custom sequence preprocess lib and application From Source

DeepStream Application Migration

  • Application Migration to DeepStream 6.0.1 from DeepStream 5.X
    • Major Application Differences with DeepStream 5.X
    • Running DeepStream 5.X compiled Apps in DeepStream 6.0.1
    • Compiling DeepStream 5.1 Apps in DeepStream 6.0.1
    • Low-level Object Tracker Library Migration from DeepStream 5.1 Apps to DeepStream 6.0.1

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
      • Adding metadata to the plugin before Gst-nvstreammux
      • New metadata fields
  • Gst-nvdspreprocess (Alpha)
    • Inputs and Outputs
    • Features
    • Custom library Interfaces
    • Gst-nvdspreprocess File Configuration Specifications
    • Gst Properties
    • Sample pipelines
  • Gst-nvinfer
    • Inputs and Outputs
    • Features
    • Gst-nvinfer File Configuration Specifications
    • Gst Properties
    • Clustering algorithms supported by nvinfer
      • cluster-mode = 0 | GroupRectangles
      • cluster-mode = 1 | DBSCAN
      • cluster-mode = 2 | NMS
      • cluster-mode = 3 | Hybrid
      • cluster-mode=4 | No clustering
    • Tensor Metadata
      • To read or parse inference raw tensor data of output layers
    • 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
    • Deepstream Triton gRPC support
    • Triton Ensemble Models
    • Custom Process interface IInferCustomProcessor for Extra Input, LSTM Loop, Output Data Postprocess
    • Tensor Metadata Output for DownStream Plugins
      • To read or parse inference raw tensor data of output layers
    • Segmentation Metadata
  • Gst-nvtracker
    • Inputs and Outputs
    • Gst Properties
    • NvDsTracker API for Low-Level Tracker Library
    • NvMultiObjectTracker : A Reference Low-Level Tracker Library
    • Unified Tracker Architecture for Composable Multi-Object Tracker
    • Work Flow and Core Modules in The NvMultiObjectTracker Library
      • Data Association
      • Target Management and Error Handling
      • State Estimation
      • Motion-based Target Re-Association
      • Bounding-box Unclipping
      • Configuration Parameters
    • IOU Tracker
    • NvDCF Tracker
      • Visual Tracking
      • Data Association
      • Visualization of Sample Outputs and Correlation Responses
        • PeopleNet + NvDCF
        • DetectNet_v2 + NvDCF
        • DetectNet_v2 (w/ interval=2) + NvDCF
      • Configuration Parameters
    • DeepSORT Tracker (Alpha)
      • Re-ID
        • Re-ID Similarity Score
        • Setup Official Re-ID Model
      • Data Association
      • Customize Re-ID Model
      • Configuration Parameters
      • Implementation Details and Reference
    • Low-Level Tracker Comparisons and Tradeoffs
    • How to Implement a Custom Low-Level Tracker Library
  • Gst-nvstreammux
    • Inputs and Outputs
    • Features
    • Gst Properties
  • Gst-nvstreammux New (Beta)
    • Inputs and Outputs
    • Features
    • Gst Properties
    • Mux Config Properties
    • NvStreamMux Tuning Solutions for specific use cases
      • 1. Aim
      • 2. Important Tuning parameters
      • 3. Video + Audio muxing Use cases
        • 3.1. Video and Audio muxing; file sources of different fps
        • 3.2 Video and Audio muxing; RTMP/RTSP sources
      • 4. Troubleshooting
        • 4.1 GstAggregator plugin -> filesink does not write data into the file
        • 4.2 nvstreammux WARNING “Lot of buffers are being dropped”
    • Known Issues and FAQ
      • 1. Observing video and/or audio stutter (low framerate)
      • 2. Sink plugin shall not move asynchronously to PAUSED
      • 3. Heterogeneous batching
      • 4. Adaptive Batching
      • 5. Optimizing nvstreammux config for low-latency vs Compute
      • 6. Latency Measurement API Usage guide for audio
  • Gst-nvstreamdemux
    • Inputs and Outputs
      • Use case 1
      • Use case 2
      • Use case 3
  • Gst-nvmultistreamtiler
    • Inputs and Outputs
    • Features
    • Gst Properties
  • Gst-nvdsosd
    • Inputs and Outputs
    • Features
    • Gst Properties
  • Gst-nvdsvideotemplate
    • Inputs and Outputs
    • Features
    • customlib_impl Interfaces
    • Gst Properties
    • Sample pipelines
  • Gst-nvdsaudiotemplate
    • Inputs and Outputs
    • Features
    • customlib_impl Interfaces
    • 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
      • Inputs and Outputs
      • Features
      • Gst Properties
    • Encoder
      • Inputs and Outputs
      • Features
      • Gst Properties
  • 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_msgapi_connect(): Create a Connection
      • nvds_msgapi_send() and nvds_msgapi_send_async(): Send an event
      • nvds_msgapi_subscribe(): Consume data by subscribing to topics
      • nvds_msgapi_do_work(): Incremental Execution of Adapter Logic
      • nvds_msgapi_disconnect(): Terminate a Connection
      • nvds_msgapi_getversion(): Get Version Number
      • nvds_msgapi_get_protocol_name(): Get name of the protocol
      • nvds_msgapi_connection_signature(): Get Connection signature
    • nvds_kafka_proto: Kafka Protocol Adapter
      • Installing Dependencies
      • Using the Adapter
      • Configuring Protocol Settings
      • Programmatic Integration
      • Security for Kafka
    • Azure MQTT Protocol Adapter Libraries
      • Installing Dependencies
      • Setting Up Azure IoT
      • Configuring Adapter Settings
      • Using the Adapter
        • Connection Details for the Device Client Adapter
        • Connection Details for the Module Client Adapter
      • Monitor Adapter Execution
        • Azure device client library log messages
        • Azure Module Client Library Log Messages
      • Message Topics and Routes
    • AMQP Protocol Adapter
      • Installing Dependencies
      • AMQP broker
      • Configure Adapter Settings
      • Using the Adapter
      • Programmatic Integration
      • Monitor Adapter Execution
    • REDIS Protocol Adapter
      • Installing Dependencies
      • REDIS server
      • Configure Adapter Settings
      • Using the Adapter
      • Programmatic Integration
      • Monitor Adapter Execution
    • nv_msgbroker: Message Broker interface
      • nv_msgbroker_connect(): Create a Connection
      • nv_msgbroker_send_async(): Send an event asynchronously
      • nv_msgbroker_subscribe(): Consume data by subscribing to topics
      • nv_msgbroker_disconnect(): Terminate a Connection
      • nv_msgbroker_version(): Get Version Number
      • Autoreconnect feature
      • nvds_logger: Logging Framework
        • Enabling Logging
        • Filtering Logs
        • Retiring and Managing Logs
        • Generating Logs
  • Gst-nvdsanalytics
    • Inputs and Outputs
    • Features
    • Gst Properties
    • Configuration File Parameters
  • Gst-nvdsasr
    • Inputs and Outputs
    • Features
    • DS-Riva ASR Yaml File Configuration Specifications
    • Gst Properties
      • Riva ASR model data generation and gRPC installation
  • Gst-nvds_text_to_speech (Alpha)
    • Inputs and Outputs
    • Features
    • DS-Riva TTS Yaml File Configuration Specifications
    • Gst Properties
      • Riva TTS Service Initiation
      • gRPC C++ Installation
    • Sample Application
  • Gst-nvdsudpsrc
    • Inputs and Outputs
    • Features
    • Gst Properties

DeepStream Troubleshooting and FAQ

  • Troubleshooting
    • You are migrating from DeepStream 5.x to DeepStream 6.0.1
    • “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
    • 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)
    • Stale frames observed on RTSP output
    • Troubleshooting in NvDCF Parameter Tuning
      • Flickering Bbox
      • Frequent tracking ID changes although no nearby objects
      • Frequent tracking ID switches to the nearby objects
      • Error while running ONNX / Explicit batch dimension networks
    • DeepStream plugins failing to load without DISPLAY variable set when launching DS dockers
    • Nvidia driver installation issues
      • 1. [When user expect to use Display window]
      • 2. [When user expect to not use a Display window]
    • Nvidia TensorRT installation issues
    • Graph Composer Troubleshooting
      • My component is not visible in the composer even after registering the extension with registry
      • My component is getting registered as an abstract type.
      • When executing a graph, the execution ends immediately with the warning “No system specified. Nothing to do”
  • Frequently Asked Questions
    • DeepStream General topics
      • How do I uninstall DeepStream?
      • What types of input streams does DeepStream 6.0.1 support?
      • What’s the throughput of H.264 and H.265 decode on dGPU (Tesla)?
      • How can I run the DeepStream sample application in debug mode?
      • Where can I find the DeepStream sample applications?
      • How can I verify that CUDA was installed correctly?
      • How can I interpret frames per second (FPS) display information on console?
      • My DeepStream performance is lower than expected. How can I determine the reason?
      • How can I specify RTSP streaming of DeepStream output?
      • What is the official DeepStream Docker image and where do I get it?
      • What is the recipe for creating my own Docker image?
      • How can I display graphical output remotely over VNC? How can I determine whether X11 is running?
      • Why does the deepstream-nvof-test application show the error message “Device Does NOT support Optical Flow Functionality” if run with NVIDIA Tesla P4 or NVIDIA Jetson Nano, Jetson TX2, or Jetson TX1?
      • Why is the Gst-nvstreammux plugin required in DeepStream 4.0+?
      • Why is a Gst-nvegltransform plugin required on a Jetson platform upstream from Gst-nveglglessink?
      • How do I profile DeepStream pipeline?
      • How can I check GPU and memory utilization on a dGPU system?
      • What is the approximate memory utilization for 1080p streams on dGPU?
      • When deepstream-app is run in loop on Jetson AGX Xavier using “while true; do deepstream-app -c <config_file>; done;”, after a few iterations I see low FPS for certain iterations. Why is that?
      • Why do I get the error Makefile:13: *** "CUDA_VER is not set".  Stop when I compile DeepStream sample applications?
      • How can I construct the DeepStream GStreamer pipeline?
      • The property bufapi-version is missing from nvv4l2decoder, what to do?
      • Why am I getting “ImportError: No module named google.protobuf.internal when running convert_to_uff.py on Jetson AGX Xavier”?
      • Does DeepStream Support 10 Bit Video streams?
      • What is the difference between batch-size of nvstreammux and nvinfer? What are the recommended values for nvstreammux batch-size?
      • Why do some caffemodels fail to build after upgrading to DeepStream 6.0.1?
      • How do I configure the pipeline to get NTP timestamps?
      • Why is the NTP timestamp value 0?
      • How to handle operations not supported by Triton Inference Server?
      • Why do I see confidence value as -0.1.?
      • How to use the OSS version of the TensorRT plugins in DeepStream?
      • Why do I see the below Error while processing H265 RTSP stream?
      • Why do I observe a lot of buffers being dropped when running deepstream-nvdsanalytics-test application on Jetson Nano ?
      • Why do I observe: A lot of buffers are being dropped. When running live camera streams even for few or single stream, also output looks jittery?
      • Why does the RTSP source used in gst-launch pipeline through uridecodebin show blank screen followed by the error - WARNING: from element /GstPipeline:pipeline0/GstNvStreamMux:m: No Sources found at the input of muxer. Waiting for sources?
      • What if I do not get expected 30 FPS from camera using v4l2src plugin in pipeline but instead get 15 FPS or less than 30 FPS?
      • On Jetson platform, I get same output when multiple Jpeg images are fed to nvv4l2decoder using multifilesrc plugin. Why is that?
      • How do I obtain individual sources after batched inferencing/processing? What are the sample pipelines for nvstreamdemux?
      • Why do I encounter such error while running Deepstream pipeline memory type configured and i/p buffer mismatch ip_surf 0 muxer 3?
      • How does secondary GIE crop and resize objects?
      • How to save frames from GstBuffer?
      • What are different Memory types supported on Jetson and dGPU?
      • What are different Memory transformations supported on Jetson and dGPU?
      • Why does my image look distorted if I wrap my cudaMalloc’ed memory into NvBufSurface and provide to NvBufSurfTransform?
      • Why am I getting following waring when running deepstream app for first time?
      • How to find out the maximum number of streams supported on given platform?
      • How to find the performance bottleneck in DeepStream?
      • How to fix “cannot allocate memory in static TLS block” error?
    • Smart Record
      • Does smart record module work with local video streams?
      • Are multiple parallel records on same source supported?
      • What if I forgot to stop the recording?
      • I started the record with a set duration. Can I stop it before that duration ends?
      • What if I don’t set default duration for smart record?
      • What if I don’t set video cache size for smart record?
      • What is maximum duration of data I can cache as history for smart record?
      • Can I record the video with bounding boxes and other information overlaid?
    • Triton
      • Can Jetson platform support the same features as dGPU for Triton plugin?
      • Can Gst-nvinfereserver (DeepSream Triton plugin) run on Nano platform?
      • How to enable TensorRT optimization for Tensorflow and ONNX models?
      • How to tune GPU memory for Tensorflow models?
      • Can Gst-nvinferserver support models cross processes or containers?
      • Can users set different model repos when running multiple Triton models in single process?
      • What is the difference between DeepStream classification and Triton classification?
      • Why is max_batch_size: 0 used in some Triton model config files (samples/triton_model_repo/*/config.pbtxt)?
      • How to support Triton ensemble model?
      • Why am I getting error Could not get EGL display connection while running deepstream sample application?
      • Does Gst-nvinferserver support Triton multiple instance groups?
      • Can Gst-nvinferserver support inference on multiple GPUs?
      • What is batch-size differences for a single model in different config files (gie group in source, config_inferserver.., and Triton model’s config.pbtxt)?
      • How to use NVTX for profiling?

Graph Composer

  • Introduction
    • Graph Composer Ecosystem
    • Contents of the release
  • Graph Specification
    • Concepts
      • Graph
      • SubGraph
      • Node
      • Components
      • Edges
      • Extension
    • Graph File Format
  • System Requirements
  • Installation
  • Application Workflow
    • Launch Composer
    • Sync Extensions
    • Load Graph
    • Deploy Graph
  • Creating an AI Application
    • Launch Composer
    • Drag and Drop Components
    • Configure Components
    • Connect Components
    • Add GStreamer Scheduler
    • Count Number Of People
    • Save Graph
    • Use Multiple inputs
    • Runtime add/remove inputs
  • Reference graphs
    • Installing the reference graphs
    • deepstream-test1
      • Graph Files
      • Graph
      • Sample Output
    • deepstream-test2
      • Graph Files
      • Graph
      • Sample Output
    • deepstream-test3
      • Graph Files
      • Graph
      • Sample Output
    • deepstream-test4
      • Graph Files
      • Graph
      • Sample Output
    • deepstream-test5
      • Graph and related files
      • Graph
      • Sample Output
    • deepstream-runtime-src-add-del
      • Graph Files
      • Graph
      • Sample Output
    • deepstream-template-plugin
      • Graph Files
      • Graph
      • Sample Output
    • deepstream-app
      • Graph Files
    • deepstream-audio
      • Graph files
      • Graph
      • Sample Output
    • deepstream-360d
      • Graph and related files
      • Graph
      • Sample Output
    • deepstream-triton
      • Graph and related files
      • Graph
      • Sample Output
    • deepstream-camera
      • Graph and related files
      • Graph
      • Sample Output
    • deepstream-action-recognition
      • Graph and related files
      • Graph
      • Sample Output
    • deepstream-subgraph
      • Graph and related files
      • Graph
      • Sample Output
  • Development Workflow
    • Sync Extensions
      • Using command-line
      • Using Composer UI
    • Develop New Extension
      • Using command-line
        • Generating a non-DeepStream (GStreamer) extension
        • Generating a DeepStream (GStreamer) extension
      • Using Composer UI
    • Create and test graph
  • Developing Extensions for DeepStream
    • Extension and component factory registration boilerplate
    • A simple DeepStream component
    • Implementation of INvDsInPlaceDataHandler
    • Controlling Properties
    • Triggering Actions
    • Handling signal callbacks
    • Implementation of an Configuration Provider component
  • DeepStream Components
    • Interfaces
      • Element - INvDsElement
      • I/Os - INvDsIO/INvDsInput/INvDsOutput
      • Connections - INvDsConnection
      • DeepStream Domain Component - INvDsComponent
      • Probe - INvDsProbe
      • Probe Callback Implementation - INvDsInPlaceDataHandler
      • Action - INvDsAction
      • Signal - INvDsSignal
      • Element Property Controller – INvDsPropertyController
      • Configurations – INvDsConfigComponent template and specializations
      • INvDsInferModelConfigComponent
      • INvDsVideoTemplatePluginConfigComponent / INvDsAudioTemplatePluginConfigComponent
    • Data Components
      • GstBufferHandle
      • NvBufSurfaceHandle
      • NvBufAudioHandle
      • NvDsBatchMetaHandle
    • Basic Components
      • I/Os
    • Connections
      • NvDsConnection
      • NvDsMultiSrcConnection
    • Probes
      • NvDsProbe
      • NvDsProbeConnector
      • NvDsScheduler
  • Registry
    • Repository Manager
      • NVIDIA Cloud Repository
      • Local Workspace
    • Cache
    • Extension Registration
    • Installing graphs for deployment
  • Registry Command Line Interface
    • cache
    • repo
      • repo clean
      • repo list
      • repo info
      • repo sync
    • extn
      • extn add
      • extn sync
      • extn import
      • extn list
      • extn info
      • extn versions
      • extn variants
      • extn dependencies
    • comp
      • comp list
      • comp info
    • graph
      • graph install
  • Composer
    • User Interface
      • Menu Bar
      • Toolbar
      • Component List
    • Create New Application
    • Open and Save Application Graphs
    • Compose an Application Graph
      • Finding the right component
      • Creating a Component Instance
      • Understanding the Component Handles
        • Linking and Unlinking components
      • Node
      • Setting up a Connection from an Input to an Output
      • Changing the Component Properties
      • Editor Features
      • Subgraph
    • Run Graph
      • Options
    • Build Container Image
      • Options
    • Generate Gstreamer Extension
      • Options
    • Restrictions
  • Graph Execution Engine
  • Container Builder
    • Prerequisites
    • Container Builder Features
    • Container Builder Tool Usage
    • Run Container Builder
    • Container Builder Configuration
    • A Basic Example of Container Builder Configuration
    • A Multi-Stage Example
    • Container builder main control section specification
    • Container dockerfile stage section specification

Extensions Manual

  • NvDsAnalyticsExt
    • Components
      • nvidia::deepstream::NvDsAnalytics
        • Parameters
  • NvDsBaseExt
    • Interfaces
      • nvidia::deepstream::INvDsKeyboardInput
    • Components
      • nvidia::deepstream::NvDsStaticOutput
      • nvidia::deepstream::NvDsDynamicOutput
      • nvidia::deepstream::NvDsOnRequestOutput
      • nvidia::deepstream::NvDsStaticInput
      • nvidia::deepstream::NvDsOnRequestInput
      • nvidia::deepstream::NvDsMultiOutput
      • nvidia::deepstream::NvDsProbeConnector
      • nvidia::deepstream::NvDsProbe
        • Parameters
      • nvidia::deepstream::NvDsConnection
        • Parameters
      • nvidia::deepstream::NvDsMultiSrcConnection
        • Parameters
      • nvidia::deepstream::NvDsKeyboardInput
      • nvidia::deepstream::NvDsScheduler
      • nvidia::deepstream::NvDsToGxfBridge
        • Parameters
      • nvidia::deepstream::NvGxfToDsBridge
        • Parameters
      • nvidia::deepstream::NvDsGxfObjectDataTranslator
      • nvidia::deepstream::NvDsGxfAudioClassificationDataTranslator
      • nvidia::deepstream::NvDsGxfOpticalFlowDataTranslator
      • nvidia::deepstream::NvDsGxfSegmentationDataTranslator
      • nvidia::deepstream::NvDsGxfInferTensorDataTranslator
      • nvidia::deepstream::NvDsQueue
        • Parameters
      • nvidia::deepstream::NvDsTee
        • Parameters
      • nvidia::deepstream::NvDsBufferSync
        • Parameters
  • NvDsBodyPose2D
    • Components
      • nvidia::BodyPose2D::PostProcess
        • Parameters
      • nvidia::BodyPose2D::BodyPose2dModel
        • Parameters
      • nvidia::BodyPose2D::NvDsGxfBodypose2dDataTranslator
  • NvDsCloudMsgExt
    • Components
      • nvidia::deepstream::NvDsMessage
      • nvidia::deepstream::NvDsMsgRelayTransmitter
      • nvidia::deepstream::NvDsMsgRelayReceiver
      • nvidia::deepstream::NvDsMsgBrokerC2DReceiver
        • Parameters
      • nvidia::deepstream::NvDsMsgBrokerD2CTransmitter
        • Parameters
      • nvidia::deepstream::NvDsMsgRelay
        • Parameters
      • nvidia::deepstream::NvDsMsgBroker
        • Parameters
      • nvidia::deepstream::NvDsMsgConverter
        • Parameters
      • nvidia::deepstream::NvDsMsgConvBroker
        • Parameters
  • NvDsConverterExt
    • Components
      • nvidia::deepstream::NvDsVideoConvert
        • Parameters
      • nvidia::deepstream::AudioConvert
        • Parameters
      • nvidia::deepstream::AudioResample
        • Parameters
  • NvDsDewarperExt
    • Components
      • nvidia::deepstream::NvDsAisleFilter
        • Parameters
      • nvidia::deepstream::NvDsBBoxFilter
        • Parameters
      • nvidia::deepstream::NvDsDewarper
        • Parameters
      • nvidia::deepstream::NvDsSpotChangeSignal
      • nvidia::deepstream::NvDsSpot
        • Parameters
  • NvDsEmotionExt
    • Components
      • nvidia::Emotion::NvDsEmotionTemplateLib
  • NvDsFacialLandmarks
    • Components
      • nvidia::FacialLandmarks::PostProcess
        • Parameters
      • nvidia::FacialLandmarks::PreProcess
        • Parameters
      • nvidia::FacialLandmarks::FacialLandmarksPgieModel
        • Parameters
      • nvidia::FacialLandmarks::FacialLandmarksSgieModel
        • Parameters
      • nvidia::FacialLandmarks::FacialLandmarksSgieModelV2
        • Parameters
      • nvidia::FacialLandmarks::NvDsGxfFacialLandmarksTranslator
  • NvDsGesture
    • Components
      • nvidia::Gesture::PreProcess
        • Parameters
      • nvidia::Gesture::GestureModel
        • Parameters
  • NvDsGazeExt
    • Components
      • nvidia::Gaze::NvDsGazeTemplateLib
      • nvidia::Gaze::NvDsGxfGazeDataTranslator
  • NvDsHeartRateExt
    • Components
      • nvidia::HeartRate::NvDsHeartRateTemplateLib
      • nvidia::HeartRate::NvDsGxfHeartRateDataTranslator
  • NvDsInferenceExt
    • Components
      • nvidia::deepstream::NvDsModelUpdatedSignal
      • nvidia::deepstream::NvDsInferVideoPropertyController
      • nvidia::deepstream::NvDsInferVideo
        • Parameters
      • nvidia::deepstream::NvDsAsr
        • Parameters
      • nvidia::deepstream::NvDsInferAudio
        • Parameters
      • nvidia::deepstream::NvDsPreProcess
        • Parameters
  • NvDsInferenceUtilsExt
    • Components
      • nvidia::deepstream::NvDsKittiDump
        • Parameters
      • nvidia::deepstream::NvDsFpsMeasurement
        • Parameters
      • nvidia::deepstream::NvDsLatencyMeasurement
        • Parameters
      • nvidia::deepstream::NvDsAudioClassificationPrint
        • Parameters
      • nvidia::deepstream::NvDsPerClassObjectCounting
        • Parameters
      • nvidia::deepstream::NvDsModelEngineWatchOTFTrigger
        • Parameters
      • nvidia::deepstream::NvDsRoiClassificationResultParse
        • Parameters
  • NvDsInterfaceExt
    • Interfaces
      • nvidia::deepstream::INvDsElement
      • nvidia::deepstream::INvDsIO
      • nvidia::deepstream::INvDsInput
      • nvidia::deepstream::INvDsOutput
      • nvidia::deepstream::INvDsProbe
      • nvidia::deepstream::INvDsConnection
      • nvidia::deepstream::INvDsComponent
      • nvidia::deepstream::INvDsInPlaceDataHandler
      • nvidia::deepstream::INvDsAction
      • nvidia::deepstream::INvDsSignal
      • nvidia::deepstream::INvDsPropertyController
      • nvidia::deepstream::INvDsAudioTemplatePluginConfigComponent
      • nvidia::deepstream::INvDsVideoTemplatePluginConfigComponent
      • nvidia::deepstream::INvDsInferModelConfigComponent
      • nvidia::deepstream::INvDsGxfDataTranslator
    • Components
      • nvidia::deepstream::NvBufSurfaceHandle
      • nvidia::deepstream::NvBufAudioHandle
      • nvidia::deepstream::NvDsBatchMetaHandle
      • nvidia::deepstream::GstBufferHandle
  • NvDsMuxDemuxExt
    • Components
      • nvidia::deepstream::NvDsStreamDemux
        • Parameters
      • nvidia::deepstream::NvDsStreamMux
        • Parameters
      • nvidia::deepstream::NvDsStreamDemuxNew
        • Parameters
      • nvidia::deepstream::NvDsStreamMuxNew
        • Parameters
  • NvDsOpticalFlowExt
    • Components
      • nvidia::deepstream::NvDsOpticalFlow
        • Parameters
      • nvidia::deepstream::NvDsOpticalFlowVisual
        • Parameters
  • NvDsOutputSinkExt
    • Components
      • nvidia::deepstream::NvDsFakeSink
        • Parameters
      • nvidia::deepstream::NvDsFileOut
        • Parameters
      • nvidia::deepstream::NvDsVideoRendererPropertyController
      • nvidia::deepstream::NvDsVideoRenderer
        • Parameters
      • nvidia::deepstream::NvDsRtspOut
        • Parameters
      • nvidia::deepstream::XvImageSink
        • Parameters
      • nvidia::deepstream::AlsaAudioRenderer
        • Parameters
  • NvDsSampleExt
    • Components
      • nvidia::deepstream::NvDsSampleProbeMessageMetaCreation
        • Parameters
      • nvidia::deepstream::NvDsSampleSourceManipulator
        • Parameters
      • nvidia::deepstream::NvDsSampleVideoTemplateLib
        • Parameters
      • nvidia::deepstream::NvDsSampleAudioTemplateLib
        • Parameters
      • nvidia::deepstream::NvDsSampleC2DSmartRecordTrigger
        • Parameters
      • nvidia::deepstream::NvDsSampleD2C_SRMsgGenerator
        • Parameters
  • NvDsSampleModelsExt
    • Components
      • nvidia::deepstream::NvDsResnet10_4ClassDetectorModel
        • Parameters
      • nvidia::deepstream::NvDsSecondaryCarColorClassifierModel
        • Parameters
      • nvidia::deepstream::NvDsSecondaryCarMakeClassifierModel
        • Parameters
      • nvidia::deepstream::NvDsSecondaryVehicleTypeClassifierModel
        • Parameters
      • nvidia::deepstream::NvDsSonyCAudioClassifierModel
        • Parameters
      • nvidia::deepstream::NvDsCarDetector360dModel
        • Parameters
  • NvDsSourceExt
    • Components
      • nvidia::deepstream::NvDsSourceInfoLoader
        • Parameters
      • nvidia::deepstream::NvDsStartSrAction
      • nvidia::deepstream::NvDsStopSrAction
      • nvidia::deepstream::NvDsSrDoneSignal
      • nvidia::deepstream::NvDsSingleSrcInput
        • Parameters
      • nvidia::deepstream::NvDsSourceManipulationAction
      • nvidia::deepstream::NvDsMultiSourceSmartRecordAction
      • nvidia::deepstream::NvDsMultiSrcInput
        • Parameters
      • nvidia::deepstream::NvDsMultiSrcWarpedInput
        • Parameters
      • nvidia::deepstream::NvDsRecordAction
      • nvidia::deepstream::NvDsMultiSrcInputWithRecord
        • Parameters
      • nvidia::deepstream::NvDsCameraSrcInput
        • Parameters
      • nvidia::deepstream::VideoTestSrc
        • Parameters
      • nvidia::deepstream::AudioTestSrc
        • Parameters
      • nvidia::deepstream::AlsaAudioInput
        • Parameters
  • NvDsTemplateExt
    • Components
      • nvidia::deepstream::NvDsAudioTemplate
        • Parameters
      • nvidia::deepstream::NvDsVideoTemplate
        • Parameters
  • NvDsTrackerExt
    • Components
      • nvidia::deepstream::NvDsTracker
        • Parameters
  • NvDsTranscodeExt
    • Components
      • nvidia::deepstream::NvDsJpegDecoder
        • Parameters
      • nvidia::deepstream::NvDsVideoDecoder
        • Parameters
      • nvidia::deepstream::NvDsH264Encoder
        • Parameters
      • nvidia::deepstream::NvDsH265Encoder
        • Parameters
  • NvDsTritonExt
    • Components
      • nvidia::deepstream::NvDsTriton
        • Parameters
  • NvDsVisualizationExt
    • Components
      • nvidia::deepstream::NvDsOSDPropertyController
      • nvidia::deepstream::NvDsOSD
        • Parameters
      • nvidia::deepstream::NvDsTiler
        • Parameters
      • nvidia::deepstream::NvDsSegVisual
        • Parameters
      • nvidia::deepstream::NvDsBlender
        • Parameters
      • nvidia::deepstream::NvDsTilerEventHandler
        • Parameters

DeepStream API Guide

  • DeepStream API Guides

DeepStream Legal Information

  • DeepStream Legal Information
    • Notice
    • Trademarks
    • Copyright

DeepStream Feedback

  • Feedback form
    • Request Documentation Fix
DeepStream
  • Docs »
  • Search

© Copyright 2021-2022, NVIDIA. Last updated on Mar 08, 2022.

Built with Sphinx using a theme provided by Read the Docs.