Any data that is needed during callback function can be passed as userData. What are different Memory types supported on Jetson and dGPU? How can I run the DeepStream sample application in debug mode? Sample Helm chart to deploy DeepStream application is available on NGC. Sink plugin shall not move asynchronously to PAUSED, 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, Connection Details for the Device Client Adapter, Connection Details for the Module Client Adapter, 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, DS-Riva ASR Yaml File Configuration Specifications, DS-Riva TTS Yaml File Configuration Specifications, You are migrating from DeepStream 5.x to DeepStream 6.0, 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, 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. How do I obtain individual sources after batched inferencing/processing? Therefore, a total of startTime + duration seconds of data will be recorded. By default, the current directory is used. To learn more about these security features, read the IoT chapter. I'll be adding new github Issues for both items, but will leave this issue open until then. Only the data feed with events of importance is recorded instead of always saving the whole feed. The following minimum json message from the server is expected to trigger the Start/Stop of smart record. The message format is as follows: Receiving and processing such messages from the cloud is demonstrated in the deepstream-test5 sample application. Building Intelligent Video Analytics Apps Using NVIDIA DeepStream 5.0 It takes the streaming data as input - from USB/CSI camera, video from file or streams over RTSP, and uses AI and computer vision to generate insights from pixels for better understanding of the environment. Unable to start the composer in deepstream development docker. do you need to pass different session ids when recording from different sources? Native TensorRT inference is performed using Gst-nvinfer plugin and inference using Triton is done using Gst-nvinferserver plugin. DeepStream is a streaming analytic toolkit to build AI-powered applications. The performance benchmark is also run using this application. Last updated on Feb 02, 2023. How do I configure the pipeline to get NTP timestamps? See NVIDIA-AI-IOT Github page for some sample DeepStream reference apps. Lets go back to AGX Xavier for next step. Learn More. The source code for this application is available in /opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-app. See the deepstream_source_bin.c for more details on using this module. Why do I observe: A lot of buffers are being dropped. Optimizing nvstreammux config for low-latency vs Compute, 6. Freelancer projects vlsi embedded Jobs, Employment | Freelancer What is the difference between batch-size of nvstreammux and nvinfer? Smart Video Record DeepStream 6.1.1 Release documentation How do I configure the pipeline to get NTP timestamps? GstBin which is the recordbin of NvDsSRContext must be added to the pipeline. How to clean and restart? . userData received in that callback is the one which is passed during NvDsSRStart(). In existing deepstream-test5-app only RTSP sources are enabled for smart record. This parameter will ensure the recording is stopped after a predefined default duration. Modifications made: (1) based on the results of the real-time video analysis, and: (2) by the application user through external input. Copyright 2020-2021, NVIDIA. A video cache is maintained so that recorded video has frames both before and after the event is generated. If current time is t1, content from t1 - startTime to t1 + duration will be saved to file. To activate this functionality, populate and enable the following block in the application configuration file: While the application is running, use a Kafka broker to publish the above JSON messages on topics in the subscribe-topic-list to start and stop recording. After inference, the next step could involve tracking the object. See the C/C++ Sample Apps Source Details and Python Sample Apps and Bindings Source Details sections to learn more about the available apps. Here startTime specifies the seconds before the current time and duration specifies the seconds after the start of recording. Why does the RTSP source used in gst-launch pipeline through uridecodebin show blank screen followed by the error -. Following are the default values of configuration parameters: Following fields can be used under [sourceX] groups to configure these parameters. DeepStream - Smart Video Recording DeepStream - IoT Edge DeepStream - Demos DeepStream - Common Issues Transfer Learning Toolkit - Getting Started Transfer Learning Toolkit - Specification Files Transfer Learning Toolkit - StreetNet (TLT2) Transfer Learning Toolkit - CovidNet (TLT2) Transfer Learning Toolkit - Classification (TLT2) Why is a Gst-nvegltransform plugin required on a Jetson platform upstream from Gst-nveglglessink? A video cache is maintained so that recorded video has frames both before and after the event is generated. These 4 starter applications are available in both native C/C++ as well as in Python. DeepStream applications can be created without coding using the Graph Composer. There are more than 20 plugins that are hardware accelerated for various tasks. The DeepStream 360d app can serve as the perception layer that accepts multiple streams of 360-degree video to generate metadata and parking-related events. How to find out the maximum number of streams supported on given platform? Does smart record module work with local video streams? DeepStream Reference Application - deepstream-app DeepStream 6.2 Does DeepStream Support 10 Bit Video streams? How can I interpret frames per second (FPS) display information on console? deepstream-test5 sample application will be used for demonstrating SVR. With a lightning-fast response time - that's always free of charge -our customer success team goes above and beyond to make sure our clients have the best RFx experience possible . How to handle operations not supported by Triton Inference Server? smart-rec-duration= On AGX Xavier, we first find the deepstream-app-test5 directory and create the sample application: If you are not sure which CUDA_VER you have, check */usr/local/*. However, when configuring smart-record for multiple sources the duration of the videos are no longer consistent (different duration for each video). mp4, mkv), Troubleshooting in NvDCF Parameter Tuning, 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, 1. Why does my image look distorted if I wrap my cudaMalloced memory into NvBufSurface and provide to NvBufSurfTransform? The deepstream-test2 progresses from test1 and cascades secondary network to the primary network. Why am I getting ImportError: No module named google.protobuf.internal when running convert_to_uff.py on Jetson AGX Xavier? Here, start time of recording is the number of seconds earlier to the current time to start the recording. Currently, there is no support for overlapping smart record. The inference can be done using TensorRT, NVIDIAs inference accelerator runtime or can be done in the native framework such as TensorFlow or PyTorch using Triton inference server. For example, if t0 is the current time and N is the start time in seconds that means recording will start from t0 N. For it to work, the cache size must be greater than the N. smart-rec-default-duration= How can I interpret frames per second (FPS) display information on console? How to find the performance bottleneck in DeepStream? Why does my image look distorted if I wrap my cudaMalloced memory into NvBufSurface and provide to NvBufSurfTransform? What is the difference between DeepStream classification and Triton classification? Arvind Radhakrishnen auf LinkedIn: #bard #chatgpt #google #search # DeepStream supports application development in C/C++ and in Python through the Python bindings. How can I verify that CUDA was installed correctly? On Jetson platform, I get same output when multiple Jpeg images are fed to nvv4l2decoder using multifilesrc plugin. How to use the OSS version of the TensorRT plugins in DeepStream? How to tune GPU memory for Tensorflow models? The size of the video cache can be configured per use case. Smart Video Record DeepStream 5.1 Release documentation For unique names every source must be provided with a unique prefix. Below diagram shows the smart record architecture: This module provides the following APIs. With DeepStream you can trial our platform for free for 14-days, no commitment required. Which Triton version is supported in DeepStream 6.0 release? Do I need to add a callback function or something else? Video and Audio muxing; file sources of different fps, 3.2 Video and Audio muxing; RTMP/RTSP sources, 4.1 GstAggregator plugin -> filesink does not write data into the file, 4.2 nvstreammux WARNING Lot of buffers are being dropped, 5. What is the recipe for creating my own Docker image? Observing video and/or audio stutter (low framerate), 2. Which Triton version is supported in DeepStream 5.1 release? It expects encoded frames which will be muxed and saved to the file. The first frame in the cache may not be an Iframe, so, some frames from the cache are dropped to fulfil this condition. The message format is as follows: Receiving and processing such messages from the cloud is demonstrated in the deepstream-test5 sample application. For creating visualization artifacts such as bounding boxes, segmentation masks, labels there is a visualization plugin called Gst-nvdsosd. Can Gst-nvinferserver support models across processes or containers? It will not conflict to any other functions in your application. Why does the RTSP source used in gst-launch pipeline through uridecodebin show blank screen followed by the error -. Can I record the video with bounding boxes and other information overlaid? It will not conflict to any other functions in your application. The latest release of #NVIDIADeepStream SDK version 6.2 delivers powerful enhancements such as state-of-the-art multi-object trackers, support for lidar and Recording also can be triggered by JSON messages received from the cloud. What is the approximate memory utilization for 1080p streams on dGPU? Smart video record is used for event (local or cloud) based recording of original data feed. I hope to wrap up a first version of ODE services and alpha v0.5 by the end of the week, Once released I'm going to start on the Deepstream 5 upgrade, and the Smart recording will be the first new ODE action to implement. The events are transmitted over Kafka to a streaming and batch analytics backbone. When to start smart recording and when to stop smart recording depend on your design. deepstream.io Custom broker adapters can be created. Call NvDsSRDestroy() to free resources allocated by this function. # seconds before the current time to start recording. Call NvDsSRDestroy() to free resources allocated by this function. Smart-rec-container=<0/1> tensorflow python framework errors impl notfounderror no cpu devices are available in this process Copyright 2023, NVIDIA. How to fix cannot allocate memory in static TLS block error? To learn more about deployment with dockers, see the Docker container chapter. Based on the event, these cached frames are encapsulated under the chosen container to generate the recorded video. Dieser Button zeigt den derzeit ausgewhlten Suchtyp an. The graph below shows a typical video analytic application starting from input video to outputting insights. MP4 and MKV containers are supported. The property bufapi-version is missing from nvv4l2decoder, what to do? Records are the main building blocks of deepstream's data-sync capabilities. Why does my image look distorted if I wrap my cudaMalloced memory into NvBufSurface and provide to NvBufSurfTransform? This function creates the instance of smart record and returns the pointer to an allocated NvDsSRContext. What are different Memory transformations supported on Jetson and dGPU? Issue Type( questions). Path of directory to save the recorded file. Recording also can be triggered by JSON messages received from the cloud. How can I run the DeepStream sample application in debug mode? Freelancer #sensor-list-file=dstest5_msgconv_sample_config.txt, Install librdkafka (to enable Kafka protocol adaptor for message broker), Run deepstream-app (the reference application), Remove all previous DeepStream installations, Run the deepstream-app (the reference application), dGPU Setup for RedHat Enterprise Linux (RHEL), How to visualize the output if the display is not attached to the system, 1 . This function releases the resources previously allocated by NvDsSRCreate(). The DeepStream reference application is a GStreamer based solution and consists of set of GStreamer plugins encapsulating low-level APIs to form a complete graph. Why do I observe: A lot of buffers are being dropped. kafka_2.13-2.8.0/config/server.properties, configs/test5_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt, #Type - 1=FakeSink 2=EglSink 3=File 4=UDPSink 5=nvoverlaysink 6=MsgConvBroker, #(0): PAYLOAD_DEEPSTREAM - Deepstream schema payload, #(1): PAYLOAD_DEEPSTREAM_MINIMAL - Deepstream schema payload minimal, #(257): PAYLOAD_CUSTOM - Custom schema payload, #msg-broker-config=../../deepstream-test4/cfg_kafka.txt, # do a dummy poll to retrieve some message, 'HWY_20_AND_LOCUST__EBA__4_11_2018_4_59_59_508_AM_UTC-07_00', 'Vehicle Detection and License Plate Recognition', "HWY_20_AND_LOCUST__EBA__4_11_2018_4_59_59_508_AM_UTC-07_00", test5_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt, #Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP, # smart record specific fields, valid only for source type=4, # 0 = disable, 1 = through cloud events, 2 = through cloud + local events. Why I cannot run WebSocket Streaming with Composer? To enable smart record in deepstream-test5-app set the following under [sourceX] group: To enable smart record through only cloud messages, set smart-record=1 and configure [message-consumerX] group accordingly. Sink plugin shall not move asynchronously to PAUSED, 5. How can I display graphical output remotely over VNC? When running live camera streams even for few or single stream, also output looks jittery? What is the official DeepStream Docker image and where do I get it? This is currently supported for Kafka. What is the recipe for creating my own Docker image? From the pallet rack to workstation, #Rexroth&#39;s MP1000R mobile robot offers a smart, easy-to-implement material transport solution to help you boost To make it easier to get started, DeepStream ships with several reference applications in both in C/C++ and in Python. By default, Smart_Record is the prefix in case this field is not set. Can Gst-nvinfereserver (DeepSream Triton plugin) run on Nano platform? How can I determine the reason? The increasing number of IoT devices in "smart" environments, such as homes, offices, and cities, produce seemingly endless data streams and drive many daily decisions. Gst-nvdewarper plugin can dewarp the image from a fisheye or 360 degree camera. TensorRT accelerates the AI inference on NVIDIA GPU. What are different Memory types supported on Jetson and dGPU? DeepStream - Smart Video Recording DeepStream User Guide ds-doc-1 Are multiple parallel records on same source supported? Karthick Iyer auf LinkedIn: Seamlessly Develop Vision AI Applications Details are available in the Readme First section of this document. How to fix cannot allocate memory in static TLS block error? For the output, users can select between rendering on screen, saving the output file, or streaming the video out over RTSP. 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? By default, the current directory is used. Can I stop it before that duration ends? In existing deepstream-test5-app only RTSP sources are enabled for smart record. Why do some caffemodels fail to build after upgrading to DeepStream 5.1? # default duration of recording in seconds. What is the difference between DeepStream classification and Triton classification? Why do I encounter such error while running Deepstream pipeline memory type configured and i/p buffer mismatch ip_surf 0 muxer 3? In smart record, encoded frames are cached to save on CPU memory. At the bottom are the different hardware engines that are utilized throughout the application. What is batch-size differences for a single model in different config files (. What are different Memory transformations supported on Jetson and dGPU? deepstream smart record. What are the recommended values for. How does secondary GIE crop and resize objects? How to set camera calibration parameters in Dewarper plugin config file? Regarding git source code compiling in compile_stage, Is it possible to compile source from HTTP archives? To get started with Python, see the Python Sample Apps and Bindings Source Details in this guide and DeepStream Python in the DeepStream Python API Guide. Smart video recording (SVR) is an event-based recording that a portion of video is recorded in parallel to DeepStream pipeline based on objects of interests or specific rules for recording. Size of cache in seconds. The DeepStream runtime system is pipelined to enable deep learning inference, image, and sensor processing, and sending insights to the cloud in a streaming application. This is currently supported for Kafka. What is the difference between batch-size of nvstreammux and nvinfer? If you set smart-record=2, this will enable smart record through cloud messages as well as local events with default configurations. 5.1 Adding GstMeta to buffers before nvstreammux. Smart video record is used for event (local or cloud) based recording of original data feed. Deepstream - The Berlin startup for a next-den realtime platform They will take video from a file, decode, batch and then do object detection and then finally render the boxes on the screen. # Use this option if message has sensor name as id instead of index (0,1,2 etc.). 1. Can Jetson platform support the same features as dGPU for Triton plugin? Where can I find the DeepStream sample applications? Configure [source0] and [sink1] groups of DeepStream app config configs/test5_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt so that DeepStream is able to use RTSP source from step 1 and render events to your Kafka server: At this stage, our DeepStream application is ready to run and produce events containing bounding box coordinates to Kafka server: To consume the events, we write consumer.py. Why does the deepstream-nvof-test application show the error message Device Does NOT support Optical Flow Functionality ? Python Sample Apps and Bindings Source Details, DeepStream Reference Application - deepstream-app, Install librdkafka (to enable Kafka protocol adaptor for message broker), Run deepstream-app (the reference application), Remove all previous DeepStream installations, Install CUDA Toolkit 11.4.1 (CUDA 11.4 Update 1), Run the deepstream-app (the reference application), dGPU Setup for RedHat Enterprise Linux (RHEL), Install CUDA Toolkit 11.4 (CUDA 11.4 Update 1), DeepStream Triton Inference Server Usage Guidelines, Creating custom DeepStream docker for dGPU using DeepStreamSDK package, Creating custom DeepStream docker for Jetson using DeepStreamSDK package, Python Bindings and Application Development, Expected Output for the DeepStream Reference Application (deepstream-app), DeepStream Reference Application - deepstream-test5 app, IoT Protocols supported and cloud configuration, DeepStream Reference Application - deepstream-audio app, DeepStream Audio Reference Application Architecture and Sample Graphs, DeepStream Reference Application on GitHub, 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, Custom YOLO Model in the DeepStream YOLO App, NvMultiObjectTracker Parameter Tuning Guide, Configuration File Settings for Performance Measurement, IModelParser Interface for Custom Model Parsing, Configure TLS options in Kafka config file for DeepStream, Choosing Between 2-way TLS and SASL/Plain, Setup for RTMP/RTSP Input streams for testing, Pipelines with existing nvstreammux component, Reference AVSync + ASR (Automatic Speech Recognition) Pipelines with existing nvstreammux, Reference AVSync + ASR Pipelines (with new nvstreammux), Gst-pipeline with audiomuxer (single source, without ASR + new nvstreammux), DeepStream 3D Action Recognition App Configuration Specifications, Custom sequence preprocess lib user settings, Build Custom sequence preprocess lib and application From Source, Application Migration to DeepStream 6.0 from DeepStream 5.X, Major Application Differences with DeepStream 5.X, Running DeepStream 5.X compiled Apps in DeepStream 6.0, Compiling DeepStream 5.1 Apps in DeepStream 6.0, Low-level Object Tracker Library Migration from DeepStream 5.1 Apps to DeepStream 6.0, User/Custom Metadata Addition inside NvDsBatchMeta, Adding Custom Meta in Gst Plugins Upstream from Gst-nvstreammux, Adding metadata to the plugin before Gst-nvstreammux, Gst-nvdspreprocess File Configuration Specifications, Gst-nvinfer File Configuration Specifications, Clustering algorithms supported by nvinfer, To read or parse inference raw tensor data of output layers, Gst-nvinferserver File Configuration Specifications, Tensor Metadata Output for DownStream Plugins, NvDsTracker API for Low-Level Tracker Library, Unified Tracker Architecture for Composable Multi-Object Tracker, Visualization of Sample Outputs and Correlation Responses, Low-Level Tracker Comparisons and Tradeoffs, How to Implement a Custom Low-Level Tracker Library, NvStreamMux Tuning Solutions for specific usecases, 3.1Video and Audio muxing; file sources of different fps, 3.2 Video and Audio muxing; RTMP/RTSP sources, 4.1 GstAggregator plugin -> filesink does not write data into the file, 4.2 nvstreammux WARNING Lot of buffers are being dropped, 1. Object tracking is performed using the Gst-nvtracker plugin. Refer to this post for more details. To enable audio, a GStreamer element producing encoded audio bitstream must be linked to the asink pad of the smart record bin. Why do I see the below Error while processing H265 RTSP stream? My component is getting registered as an abstract type. How to find out the maximum number of streams supported on given platform? How to find the performance bottleneck in DeepStream? How do I obtain individual sources after batched inferencing/processing? DeepStream | Procurement Software For developers looking to build their custom application, the deepstream-app can be a bit overwhelming to start development. Are multiple parallel records on same source supported? Abubeker K.M, Assistant Professor Level 12, Electronics & Communication Yes, on both accounts. What is maximum duration of data I can cache as history for smart record? How to extend this to work with multiple sources? What is batch-size differences for a single model in different config files (, Create Container Image from Graph Composer, Generate an extension for GXF wrapper of GstElement, Extension and component factory registration boilerplate, Implementation of INvDsInPlaceDataHandler, Implementation of an Configuration Provider component, DeepStream Domain Component - INvDsComponent, Probe Callback Implementation - INvDsInPlaceDataHandler, Element Property Controller INvDsPropertyController, Configurations INvDsConfigComponent template and specializations, INvDsVideoTemplatePluginConfigComponent / INvDsAudioTemplatePluginConfigComponent, Set the root folder for searching YAML files during loading, Starts the execution of the graph asynchronously, Waits for the graph to complete execution, Runs all System components and waits for their completion, Get unique identifier of the entity of given component, Get description and list of components in loaded Extension, Get description and list of parameters of Component, nvidia::gxf::DownstreamReceptiveSchedulingTerm, nvidia::gxf::MessageAvailableSchedulingTerm, nvidia::gxf::MultiMessageAvailableSchedulingTerm, nvidia::gxf::ExpiringMessageAvailableSchedulingTerm, nvidia::triton::TritonInferencerInterface, nvidia::triton::TritonRequestReceptiveSchedulingTerm, nvidia::deepstream::NvDs3dDataDepthInfoLogger, nvidia::deepstream::NvDs3dDataColorInfoLogger, nvidia::deepstream::NvDs3dDataPointCloudInfoLogger, nvidia::deepstream::NvDsActionRecognition2D, nvidia::deepstream::NvDsActionRecognition3D, nvidia::deepstream::NvDsMultiSrcConnection, nvidia::deepstream::NvDsGxfObjectDataTranslator, nvidia::deepstream::NvDsGxfAudioClassificationDataTranslator, nvidia::deepstream::NvDsGxfOpticalFlowDataTranslator, nvidia::deepstream::NvDsGxfSegmentationDataTranslator, nvidia::deepstream::NvDsGxfInferTensorDataTranslator, nvidia::BodyPose2D::NvDsGxfBodypose2dDataTranslator, nvidia::deepstream::NvDsMsgRelayTransmitter, nvidia::deepstream::NvDsMsgBrokerC2DReceiver, nvidia::deepstream::NvDsMsgBrokerD2CTransmitter, nvidia::FacialLandmarks::FacialLandmarksPgieModel, nvidia::FacialLandmarks::FacialLandmarksSgieModel, nvidia::FacialLandmarks::FacialLandmarksSgieModelV2, nvidia::FacialLandmarks::NvDsGxfFacialLandmarksTranslator, nvidia::HeartRate::NvDsHeartRateTemplateLib, nvidia::HeartRate::NvDsGxfHeartRateDataTranslator, nvidia::deepstream::NvDsModelUpdatedSignal, nvidia::deepstream::NvDsInferVideoPropertyController, nvidia::deepstream::NvDsLatencyMeasurement, nvidia::deepstream::NvDsAudioClassificationPrint, nvidia::deepstream::NvDsPerClassObjectCounting, nvidia::deepstream::NvDsModelEngineWatchOTFTrigger, nvidia::deepstream::NvDsRoiClassificationResultParse, nvidia::deepstream::INvDsInPlaceDataHandler, nvidia::deepstream::INvDsPropertyController, nvidia::deepstream::INvDsAudioTemplatePluginConfigComponent, nvidia::deepstream::INvDsVideoTemplatePluginConfigComponent, nvidia::deepstream::INvDsInferModelConfigComponent, nvidia::deepstream::INvDsGxfDataTranslator, nvidia::deepstream::NvDsOpticalFlowVisual, nvidia::deepstream::NvDsVideoRendererPropertyController, nvidia::deepstream::NvDsSampleProbeMessageMetaCreation, nvidia::deepstream::NvDsSampleSourceManipulator, nvidia::deepstream::NvDsSampleVideoTemplateLib, nvidia::deepstream::NvDsSampleAudioTemplateLib, nvidia::deepstream::NvDsSampleC2DSmartRecordTrigger, nvidia::deepstream::NvDsSampleD2C_SRMsgGenerator, nvidia::deepstream::NvDsResnet10_4ClassDetectorModel, nvidia::deepstream::NvDsSecondaryCarColorClassifierModel, nvidia::deepstream::NvDsSecondaryCarMakeClassifierModel, nvidia::deepstream::NvDsSecondaryVehicleTypeClassifierModel, nvidia::deepstream::NvDsSonyCAudioClassifierModel, nvidia::deepstream::NvDsCarDetector360dModel, nvidia::deepstream::NvDsSourceManipulationAction, nvidia::deepstream::NvDsMultiSourceSmartRecordAction, nvidia::deepstream::NvDsMultiSrcWarpedInput, nvidia::deepstream::NvDsMultiSrcInputWithRecord, nvidia::deepstream::NvDsOSDPropertyController, nvidia::deepstream::NvDsTilerEventHandler, Setting up a Connection from an Input to an Output, A Basic Example of Container Builder Configuration, Container builder main control section specification, Container dockerfile stage section specification.