AV Sync in DeepStream

您所在的位置：网站首页 › deepstream ffmpeg › AV Sync in DeepStream

AV Sync in DeepStream

2023-09-22 22:41| 来源: 网络整理| 查看: 265

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) Install latest NVIDIA BSP packages 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 CUDA Toolkit 12.1 Install NVIDIA driver 525.125.06 (only for data center GPUs) Install NVIDIA driver 530.41.03, for professional and consumer GPUs (GeForce/ NVIDIA RTX/ QUADRO) Install cuda-compat-12-1 (only for data center GPUs) Install TensorRT 8.5.3.1 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) How to visualize the output if the display is not attached to the system 1 . Running with an X server by creating virtual display 2 . Running without an X server (applicable for applications supporting RTSP streaming output) Platform and OS Compatibility DeepStream Triton Inference Server Usage Guidelines dGPU Jetson Using DLA for inference Separate processes Single process Docker Containers Prerequisites A Docker Container for dGPU A Docker Container for Jetson Creating custom DeepStream dockers for dGPU or Jetson using DeepStreamSDK package Recommended Minimal L4T Setup necessary to run the new docker images on Jetson

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 Source-list and source-attr-all Groups 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 Sensor Provisioning Support over REST API (Runtime sensor add/remove capability) DeepStream Reference Application - deepstream-audio app DeepStream Audio Reference Application Architecture and Sample Graphs DeepStream Reference Application - deepstream-nmos app Application Architecture Using Easy-NMOS for NMOS Registry and Controller 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 3D Custom Manual DS3D Application Examples ds3d::dataloader - Load Custom Lib for Data Capture Load and Manage Dataloader Dataloader in User Application Implement a Custom Dataloader ds3d::datafilter- Loads Custom Lib for Input and Output Processing Load And Manage Datafilter Datafilter in User Application Implement a Custom Datafilter ds3d::datarender - Loads Custom Lib for Data Rendering Load And Manage Datarender Datarender in User Application Implement a Custom Datarender DS3D GuardDataMap Buffer Management DS3D Data Map Read DS3D Data Map Write Custom Libs Configuration Specifications Components Common Configuration Specifications libnvds_3d_dataloader_realsense Configuration Specifications libnvds_3d_depth2point_datafilter Configuration Specifications libnvds_3d_gl_datarender Configuration Specifications libnvds_3d_depth_datasource Depth file source Specific Configuration Specifications

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 Data center GPU - A30 System Configuration Application Configuration Data center GPU - A2 System Configuration Application Configuration Data center GPU - A10 System Configuration Application Configuration Data center GPU - H100 System Configuration Application Configuration Data center GPU - L40 System Configuration Application Configuration Data center GPU - L4 System Configuration Application Configuration Data center GPU - Quadro (A6000) System Configuration Application Configuration Jetson System Configuration Jetson AGX Xavier Jetson NX Jetson AGX Orin Jetson Orin NX Jetson Orin Nano

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 With REST API Sever (Alpha) Features nvds_rest_server deepstream-server-app Sensor provisioning with deepstream-test5-app How to add custom REST API support REST API endpoints implementation Handler Function Implementation Details Custom event generation Callback implementation for REST API endpoints Schema and endpoints Stream add/remove ROI Decoder Nvinfer Nvinferserver Encoder Streammux Nvvideoconvert Nvdsosd Application Instance Limitations 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 3D Depth Camera App Prerequisites Depth Color Capture to 2D Rendering Pipeline Overview Depth Color Capture to 3D Point Cloud Processing and Rendering Getting Started Run RealSense Camera for Depth Capture and 2D Rendering Examples Run 3D Depth Capture, Point Cloud filter, and 3D Points Rendering Examples DeepStream 3D Depth Camera App Configuration Specifications deepstream-3d-depth-camera [ds3d::userapp] group settings DS3D Custom Components Configuration Specifications Build application From Source DeepStream Lidar Inference App (Alpha) Prerequisites Lidar Point Cloud to 3D Point Cloud Processing and Rendering Getting Started Run Lidar Point Cloud Data File reader, Point Cloud Inferencing filter, and Point Cloud 3D rendering and data dump Examples DeepStream Lidar Inference App Configuration Specifications deepstream-lidar-inference-app [ds3d::userapp] group settings DS3D Custom Components Configuration Specifications Networked Media Open Specifications (NMOS) in DeepStream Supported Specifications Prerequisites NvDsNmos API Sample Application Gst-nvdspostprocess in DeepStream Detector models Primary Classification model Mask RCNN Model Custom Parsing functions DeepStream Can Orientation App Getting Started Prerequisites Run DeepStream Can Orientation Examples DeepStream Can Orientation App Configuration Specifications deepstream-can-orientation-app settings Custom lib libnvds_vpicanmatch.so Settings for Can Template Matching Build application From Source

DeepStream Application Migration

Application Migration to DeepStream 6.3 from DeepStream 6.2 Running DeepStream 6.2 compiled Apps in DeepStream 6.3 Compiling DeepStream 6.2 Apps in DeepStream 6.3

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 Configuration File 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 Workflow and Core Modules in The NvMultiObjectTracker Library Data Association Target Management and Error Handling State Estimation Object Re-Identification Target Re-Association Bounding-box Unclipping Configuration Parameters Low-Level Tracker Comparisons and Tradeoffs IOU Tracker NvSORT Tracker NvDeepSORT Tracker Data Association Configuration Parameters Implementation Details and Reference NvDCF Tracker Visual Tracking Data Association Configuration Parameters Setup and Usage of Re-ID Model Setup Sample Re-ID Models NVIDIA TAO ReIdentificationNet ONNX Model UFF Model (Deprecated) Re-ID Model Calibration (Optional) Customize Re-ID Model Re-ID Feature Output Setup and Visualization of Tracker Sample Pipelines People Tracking Setup PeopleNet + NvSORT PeopleNet + NvDeepSORT PeopleNet + NvDCF Vehicle Tracking Setup DetectNet_v2 + NvDCF DetectNet_v2 (w/ interval=2) + NvDCF TrafficCamNet + NvSORT TrafficCamNet + NvDeepSORT TrafficCamNet + NvDCF How to Implement a Custom Low-Level Tracker Library Gst-nvstreammux Inputs and Outputs Features Gst Properties Known Issues with Solutions and FAQ 1. gst-inspect is not updated properly when switching between legacy and new streammux Gst-nvstreammux New 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” 5. Metadata propagation through nvstreammux and nvstreamdemux 5.1 Adding GstMeta to buffers before nvstreammux. 5.2 Accessing GstMeta post nvstreammux. 5.3 Adding GstMeta post nvstreammux. 5.4 To access NvDsMeta after nvstreamdemux.src_pad 6. Cascaded Muxing Known Issues with Solutions 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 7. gst-inspect is not updated properly when switching between legacy and new streammux 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-nvdsmetautils Gst-nvdsmetainsert Inputs and Outputs Features customlib_impl Interfaces Gst Properties Use Cases & Sample Pipelines Gst-nvdsmetaextract Inputs and Outputs Features customlib_impl Interfaces Gst Properties Use Cases & Sample Pipelines 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-nvjpegenc Inputs and Outputs Features Gst Properties Gst-nvmsgconv Inputs and Outputs Features Gst Properties NvMsgConv low level library API’s 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 MQTT Protocol Adapter (Alpha) Installing Dependencies Eclipse Mosquitto 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 Work-interval configuration 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 Library YAML File Configuration Specifications Gst Properties Riva ASR Service Deployment gRPC C++ Library Installation Sample Test Application 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 Example pipelines Gst-nvdsudpsink Inputs and Outputs Features Gst Properties Example pipelines Gst-nvdspostprocess (Alpha) Inputs and Outputs Features Gst-nvdspostprocess File Configuration Specifications Gst Properties Sample pipelines Gst-nvds3dfilter Inputs and Outputs Custom library Interfaces Gst-nvds3dfilter properties Specifications Gst-nvdsucx (Alpha) Description Requirements Inputs and Outputs Gst Properties Examples Gst-nvdsxfer Inputs and Outputs Gst Properties How to test Use cases Single Stream + Multi-dGPUs Setup Multiple Streams + Multi-dGPU Setup Gst-nvvideotestsrc Outputs Gst Properties How to test Gst-nvmultiurisrcbin (Alpha) 1. Introduction 2. Features 3. How to use nvmultiurisrcbin in a pipeline 3.1 REST API payload definitions and sample curl commands for reference 3.1.1 ADD a new stream to a DeepStream pipeline 3.1.2 REMOVE a new stream to a DeepStream pipeline 4. Gst Properties 4.1 Gst Properties directly configuring nvmultiurisrcbin 4.2 Gst Properties to configure each instance of nvurisrcbin created inside this bin 4.3 Gst Properties to configure the instance of nvstreammux created inside this bin 5. Important Notes 5.1 nvmultiurisrcbin config recommendations and notes on expected behavior 6. Known Issues Gst-nvurisrcbin 1. Introduction 2. How to use nvurisrcbin in a pipeline 3. Gst Properties 3.1 Gst Properties to configure nvurisrcbin

DeepStream Troubleshooting and FAQ

Troubleshooting You are migrating from DeepStream 6.0 to DeepStream 6.3 Inference Application fails to run when the neural network is changed Performance The DeepStream application is running slowly (Jetson only) The DeepStream application is running slowly Triton Errors occur when deepstream-app fails to load plugin Gst-nvinferserver Tensorflow models are running into OOM (Out-Of-Memory) problem Troubleshooting in Tracker Setup and Parameter Tuning Flickering Bbox Frequent tracking ID changes although no nearby objects Frequent tracking ID switches to the nearby objects Setup Re-ID model Error while running ONNX / Explicit batch dimension networks 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” Miscellaneous “NvDsBatchMeta not found for input buffer” error while running DeepStream pipeline The DeepStream reference application fails to launch, or any plugin fails to load Errors occur when deepstream-app is run with a number of streams greater than 100 After removing all the sources from the pipeline crash is seen if muxer and tiler are present in the pipeline Some RGB video format pipelines worked before DeepStream 6.1 onwards on Jetson but don’t work now UYVP video format pipeline doesn’t work on Jetson Memory usage keeps on increasing when the source is a long duration containerized files(e.g. mp4, mkv) Stale frames observed on RTSP output DeepStream plugins failing to load without DISPLAY variable set when launching DS dockers Nvidia driver installation issues On Jetson, observing error : gstnvarguscamerasrc.cpp, execute:751 No cameras available deepstream(-test5)-app fail to start when [source-list] config num-source-bins=0 Sensor removal is not working as expected with nvmultiurisrcbin [corner case] Frequently Asked Questions DeepStream General topics How do I uninstall DeepStream? What types of input streams does DeepStream 6.3 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” ? Why is the Gst-nvstreammux plugin required in DeepStream 4.0+? 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 ; done;”, after a few iterations I see low FPS for certain iterations. Why is that? Why do I get the error incorrect camera parameters provided, please provide supported resolution and frame rate when I compile DeepStream sample application with source1_usb_dec_infer_resnet_int8.txt config in default setting on Jetson? 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? How to set camera calibration parameters in Dewarper plugin config file? How to get camera calibration parameters for usage in Dewarper plugin? How to minimize FPS jitter with DS application while using RTSP Camera Streams? 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 6.3? How do I configure the pipeline to get NTP timestamps? Why is the NTP timestamp value 0? 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 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? On Jetson platform, I observe lower FPS output when screen goes idle. 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? 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? How to measure pipeline latency if pipeline contains open source components Migration to newer gstreamer version Why do I get the WARNING WARNING from src_elem: No decoder available for type 'audio/mpeg, mpegversion=(int)4’ when I run deepstream-app sample configuration on DS docker containers? Why do I get the WARNING: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstlibav.so': libavfilter.so.7: cannot open shared object file: No such file or directory when using deepstream-app –version-all? On x86, why do I get below ERROR during compilation and running of application/libs/plugins : Cuda failure: the provided PTX was compiled with an unsupported toolchain NvDsInferConvert_C3ToP3Float: cuda err = the provided PTX was compiled with an unsupported toolchain.? 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? How to enable TensorRT optimization for Tensorflow and ONNX models? How to tune GPU memory for Tensorflow models? Why am I getting following warning when running deepstream app for first time? How to handle operations not supported by Triton Inference Server? Can Gst-nvinferserver support models across 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)? Profiling using NVTX

Graph Composer

Overview Concepts GXF (Graph eXecution Format) Graph Node Components Codelets Subgraph System Edges / Connection Messages Extension Graph eXecution Engine (GXE) Tools Graph Composer Registry Container Builder GXF Server GXF CLI Workflow

Platforms

Ubuntu 20.04 LTS (x86_64) Features Supported System Requirements Install Ubuntu 20.04 LTS (ARM64 Jetson) Features Supported System Requirements Install Windows 10 (x86_64) Features Supported System Requirements

Getting Started

Application Workflow Launch Graph Composer Sync Extensions Create a Graph Run Graph from Graph Composer Local System Remote System Run Graph from Command line Create Container Image from Graph Composer Local System Remote System (Windows) DeepStream Application 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-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 deepstream-3d-camera Graph and related files Graph Sample Output deepstream-ucx-test1 Graph and related files Graph Sample Output deepstream-ucx-test2 Graph and related files Graph Sample Output Development Workflow Sync Extensions Using commandline Using Composer UI Develop New Extension Using commandline Generate an extension for GXF Codelet Generate an extension for GXF wrapper of GstElement 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

Graph eXecution Format

Overview GXF Core GXF Extensions GXF Development Guide Application Development Guide LifeCycle of a Codelet The GXF Scheduler Greedy Scheduler Multithread Scheduler Epoch Scheduler SchedulingTerms PeriodicSchedulingTerm CountSchedulingTerm MessageAvailableSchedulingTerm MultiMessageAvailableSchedulingTerm BooleanSchedulingTerm AsynchronousSchedulingTerm DownstreamReceptiveSchedulingTerm TargetTimeSchedulingTerm ExpiringMessageAvailableSchedulingTerm AND Combined BTSchedulingTerm Messages Transmitter Receiver Transmitter Example Receiver Example Memory Management Extensions Development Guide Sample GXF Extension

Graph eXecution Engine

Graph Execution Engine 1. How to override the parameters that are specified in the graph file using command line options? 1. Single graph file 2. Multiple subgraph files

GXF Core APIs

GXF Core C APIs Context Create context Create a context from a shared context Destroy context Extensions Load Extensions from a file Load Extension libraries Load Metadata files Register component Graph Execution Loads a list of entities from YAML file Set the root folder for searching YAML files during loading Loads a list of entities from YAML text Activate all system components Deactivate all System components Starts the execution of the graph asynchronously Interrupt the execution of the graph Waits for the graph to complete execution Runs all System components and waits for their completion Entities Create an entity Activate an entity Deactivate an entity Destroy an entity Find an entity Find all entities Increase reference count of an entity Decrease reference count of an entity Get status of an entity Get state of an entity Notify entity of an event Components Get component type identifier Get component type name Get component name Get unique identifier of the entity of given component Add a new component Add component to entity interface Find a component in an entity Get type identifier for a component Gets pointer to component Primitive Parameters 64-bit floating point Set Get 64-bit signed integer Set Get 64-bit unsigned integer Set Get 32-bit signed integer Set Get String parameter Set Get Boolean Set Get Handle Set Get Vector Parameters Set 1-D Vetor Parameters Set 2-D Vetor Parameters Get 1-D Vetor Parameters Get 2-D Vetor Parameters Information Queries Get Meta Data about the GXF Runtime Get description and list of components in loaded Extension Get description and list of parameters of Component Get parameter type description Get flag type description Get parameter description Redirect logs to a file Miscellaneous Get string description of error GXF Python APIs Context Create context Destroy context Extensions Load Extensions from a file Graph Loads a list of entities from YAML file Activate all system components Deactivate all System components Starts the execution of the graph asynchronously Waits for the graph to complete execution Runs all System components and waits for their completion Entities Find an entity Get status of an entity Components Find a component in an entity Primitive Parameters 64-bit floating point Set Get 64-bit signed integer Set Get 64-bit unsigned integer Set Get 32-bit signed integer Set Get String parameter Set Get Boolean Set Get Handle Set Get Vector Parameters Set 1-D Vetor Parameters Set 2-D Vetor Parameters Get 1-D Vetor Parameters Get 2-D Vetor Parameters

Extensions Manual

CudaExtension Components nvidia::gxf::CudaStream nvidia::gxf::CudaStreamId nvidia::gxf::CudaEvent nvidia::gxf::CudaStreamPool Parameters nvidia::gxf::CudaStreamSync Parameters GXF Stream Sync Signaler Waiter GxfStreamExtension Components nvidia::gxf::GxfStreamSync GXF Stream Sync Workflow At the Signaler codelet At the Waiter Codelet Example StandardExtension Interfaces nvidia::gxf::Codelet nvidia::gxf::Clock nvidia::gxf::System nvidia::gxf::Queue nvidia::gxf::Router nvidia::gxf::Transmitter nvidia::gxf::Receiver nvidia::gxf::Scheduler nvidia::gxf::SchedulingTerm nvidia::gxf::Allocator nvidia::gxf::Monitor Components nvidia::gxf::RealtimeClock Parameters nvidia::gxf::ManualClock Parameters nvidia::gxf::SystemGroup nvidia::gxf::MessageRouter nvidia::gxf::RouterGroup nvidia::gxf::DoubleBufferTransmitter Parameters nvidia::gxf::DoubleBufferReceiver Parameters nvidia::gxf::Connection Parameters nvidia::gxf::PeriodicSchedulingTerm Parameters nvidia::gxf::CountSchedulingTerm Parameters nvidia::gxf::TargetTimeSchedulingTerm Parameters nvidia::gxf::DownstreamReceptiveSchedulingTerm Parameters nvidia::gxf::MessageAvailableSchedulingTerm Parameters nvidia::gxf::MultiMessageAvailableSchedulingTerm Parameters nvidia::gxf::ExpiringMessageAvailableSchedulingTerm Parameters nvidia::gxf::BooleanSchedulingTerm nvidia::gxf::AsynchronousSchedulingTerm nvidia::gxf::GreedyScheduler Parameters nvidia::gxf::MultiThreadScheduler Parameters nvidia::gxf::BlockMemoryPool Parameters nvidia::gxf::UnboundedAllocator Parameters nvidia::gxf::Tensor nvidia::gxf::Timestamp nvidia::gxf::Metric Parameters nvidia::gxf::JobStatistics Parameters nvidia::gxf::Broadcast Parameters nvidia::gxf::Gather Parameters nvidia::gxf::TensorCopier Parameters nvidia::gxf::TimedThrottler Parameters nvidia::gxf::Vault Parameters nvidia::gxf::Subgraph Parameters nvidia::gxf::EndOfStream nvidia::gxf::Synchronization Parameters signed char unsigned char short int short unsigned int int unsigned int long int long unsigned int float double bool Python Bindings Clock Receiver Transmitter PrimitiveType Shape MemoryStorageType Tensor Allocator Python Codelets General Concepts Implenting a Python Codelet Implementing Class Adding Python Codelet to the Graph Accessing Parameters Accessing other Components NetworkExtension Interfaces Components nvidia::gxf::TcpClient Parameters nvidia::gxf::TcpServer Parameters NvTritonExt Components nvidia::triton::TritonServer Parameters nvidia::triton::TritonInferencerInterface nvidia::triton::TritonInferencerImpl Parameters nvidia::triton::TritonInferenceRequest Parameters nvidia::triton::TritonInferenceResponse Parameters nvidia::triton::TritonOptions nvidia::triton::TritonRequestReceptiveSchedulingTerm Parameters SerializationExtension Interfaces nvidia::gxf::ComponentSerializer Components nvidia::gxf::EntityRecorder Parameters nvidia::gxf::EntityReplayer Parameters nvidia::gxf::StdComponentSerializer Parameters MultimediaExtension Components nvidia::gxf::AudioBuffer nvidia::gxf::VideoBuffer VideoEncoderExtension Components nvidia::gxf::VideoEncoderRequest Parameters nvidia::gxf::VideoEncoderResponse Parameters nvidia::gxf::VideoEncoderContext Parameters VideoDecoderExtension Components nvidia::gxf::VideoDecoderRequest Parameters nvidia::gxf::VideoDecoderResponse Parameters nvidia::gxf::VideoDecoderContext Parameters Behavior Trees General Concept Behavior Tree Codelets Constant Behavior Parallel Behavior Repeat Behavior Selector Behavior Sequence Behavior Switch Behavior Timer Behavior UCX Extension Description Requirements Components UcxContext Parameters UcxTransmitter Parameters UcxReceiver Parameters UcxComponentSerializer Parameters UcxEntitySerializer Parameters UcxSerializationBuffer Parameters Example HttpExtension Interfaces nvidia::gxf::HttpClient Components nvidia::gxf::HttpServer Parameters nvidia::gxf::CppRestHttpClient Parameters GrpcExtension Interfaces Components nvidia::gxf::GrpcServer Parameters NvDs3dProcessingExt Components nvidia::deepstream::NvDs3dSrc Parameters nvidia::deepstream::NvDs3dSink Parameters nvidia::deepstream::NvDs3dFilter Parameters nvidia::deepstream::NvDs3dDataDepthInfoLogger Parameters nvidia::deepstream::NvDs3dDataColorInfoLogger Parameters nvidia::deepstream::NvDs3dDataPointCloudInfoLogger Parameters NvDsActionRecognitionExt Components nvidia::deepstream::NvDsActionRecognition2D Parameters nvidia::deepstream::NvDsActionRecognition3D Parameters 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 NvDsGazeExt Components nvidia::Gaze::NvDsGazeTemplateLib nvidia::Gaze::NvDsGxfGazeDataTranslator NvDsGesture Components nvidia::Gesture::PreProcess Parameters nvidia::Gesture::GestureModel Parameters 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 nvidia::deepstream::NvDsMetaDeserialize Parameters nvidia::deepstream::NvDsMetaSerialize 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 NvDsUcxExt Components nvidia::deepstream::NvDsUcxClientSink Parameters nvidia::deepstream::NvDsUcxClientSrc Parameters nvidia::deepstream::NvDsUcxServerSink Parameters nvidia::deepstream::NvDsUcxServerSrc Parameters NvDsUdpExt Components nvidia::deepstream::NvDsUdpSink Parameters nvidia::deepstream::NvDsUdpSrc 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

Tools

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 File Menu Edit Menu Registry Menu Graph Menu Tools Menu Window Menu Help Menu Context Menu 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 Entity Node Setting up a Connection from an Input to an Output Changing the Component Properties Editor Features Subgraph Backdrop Extend a Graph Run Graph Options Build Container Image Options Generate Gstreamer Extension Options Remote Access Comparison of available options Omniverse Streaming Client Installation and Usage Configuration Server Client WebRTC streaming Current Limitations: Restrictions Trouble Shooting 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 GXF Command Line Interface stat config dump

FAQ Guide

FAQ General How to add new extension? Registry How can I know which extensions synchronized to registry cache correspond to a specific repository? The registry failed to perform an operation and reported an error message. How can I get more information on why the operation failed? How can I change the location of the registry logs? Container Builder In the main control section, why is the field container_builder required? In the list of local_copy_files, if src is a folder, Any difference for dst ends with ‘/’ or not? What happens if unsupported fields are added into each section of the YAML file? During container builder installing graphs, sometimes there are unexpected errors happening while downloading manifests or extensions from registry. And once it happens, container builder may return errors again and again. How to clean and restart? Regarding git source code compiling in compile_stage, Is it possible to compile source from HTTP archives? Container builder fails to run with the following error: Composer What is the GPU requirement for running the Composer? Can I run Composer on iGPU? Why can’t I paste a component after copied one? Why I cannot run WebSocket Streaming with Composer? Unable to start the composer in deepstream development docker? Unable to right-click in composer when run through ov-streaming? Composer throws the error Registry Model update failed in the console

DeepStream API Guide

DeepStream API Guides

DeepStream Legal Information

DeepStream Legal Information Notice Trademarks Copyright

DeepStream Feedback

Feedback form Request Documentation Fix

【本文地址】

AV Sync in DeepStream

AV Sync in DeepStream

今日新闻

推荐新闻