NVIDIA defined NvDsMetaType will be present in the range from NVDS_BATCH_META to NVDS_START_USER_META. NvBbox_Coords. What is maximum duration of data I can cache as history for smart record? Regarding git source code compiling in compile_stage, Is it possible to compile source from HTTP archives? The Python bindings source code and pre-built wheels are now available on GitHub. NvOSD_Mode; NvOSD_Arrow_Head_Direction. Custom broker adapters can be created. Optimizing nvstreammux config for low-latency vs Compute, 6. A list of parameters must be defined within the config file using the proto-cfg entry within the message-broker section as shown in the example below. DeepStream supports application development in C/C++ and in Python through the Python bindings. Last updated on Apr 04, 2023.
JetPack SDK | NVIDIA Developer The runtime packages do not include samples and documentations while the development packages include these and are intended for development. Running with an X server by creating virtual display, 2 . How can I run the DeepStream sample application in debug mode? How can I display graphical output remotely over VNC? Once the frames are in the memory, they are sent for decoding using the NVDEC accelerator. How to get camera calibration parameters for usage in Dewarper plugin? There are more than 20 plugins that are hardware accelerated for various tasks. Could you please help with this. 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, 4.1 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, 5.1 nvmultiurisrcbin config recommendations and notes on expected behavior, 3.1 Gst Properties to configure nvurisrcbin, You are migrating from DeepStream 6.0 to DeepStream 6.2, Application fails to run when the neural network is changed, The DeepStream application is running slowly (Jetson only), The DeepStream application is running slowly, 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, Frequent tracking ID changes although no nearby objects, Frequent tracking ID switches to the nearby objects, Error while running ONNX / Explicit batch dimension networks, My component is not visible in the composer even after registering the extension with registry. How can I construct the DeepStream GStreamer pipeline? See NVIDIA-AI-IOT GitHub page for some sample DeepStream reference apps. For developers looking to build their custom application, the deepstream-app can be a bit overwhelming to start development. To make it easier to get started, DeepStream ships with several reference applications in both in C/C++ and in Python. On Jetson platform, I observe lower FPS output when screen goes idle. How to use the OSS version of the TensorRT plugins in DeepStream? The performance benchmark is also run using this application. DeepStream applications can be orchestrated on the edge using Kubernetes on GPU. Example Notes. Can I stop it before that duration ends? Enabling and configuring the sample plugin. In the main control section, why is the field container_builder required?
DeepStream - Intelligent Video Analytics Demo | NVIDIA NGC How can I determine the reason? Nothing to do, 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 dont work now, UYVP video format pipeline doesnt work on Jetson, Memory usage keeps on increasing when the source is a long duration containerized files(e.g. Accelerated Computing Intelligent Video Analytics DeepStream SDK yingliu February 3, 2023, 9:59am 1 DeepStream 6.2 is now available for download!
DeepStream SDK | NVIDIA Developer What are the recommended values for. These 4 starter applications are available in both native C/C++ as well as in Python. DeepStream SDK features hardware-accelerated building blocks, called plugins that bring deep neural networks and other complex processing tasks into a stream . Jetson: JetPack: 5.1 , NVIDIA CUDA: 11.4, NVIDIA cuDNN: 8.6, NVIDIA TensorRT: 8.5.2.2 , NVIDIA Triton 23.01, GStreamer 1.16.3 T4 GPUs (x86): Driver: R525+, CUDA: 11.8 , cuDNNs: 8.7+, TensorRT: 8.5.2.2, Triton 22.09, GStreamer 1.16.3. How can I verify that CUDA was installed correctly? DeepStream features sample. My DeepStream performance is lower than expected. Why do I observe: A lot of buffers are being dropped. How to tune GPU memory for Tensorflow models? How to handle operations not supported by Triton Inference Server? Sink plugin shall not move asynchronously to PAUSED, 5.
This post series addresses both challenges. Running with an X server by creating virtual display, 2 .
Announcing DeepStream 6.0 - NVIDIA Developer Forums Metadata propagation through nvstreammux and nvstreamdemux. The inference can use the GPU or DLA (Deep Learning accelerator) for Jetson AGX Xavier and Xavier NX. 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. Streaming data analytics use cases are transforming before your eyes. comma separated URI list of sources; URI of the file or rtsp source Optimum memory management with zero-memory copy between plugins and the use of various accelerators ensure the highest performance. Using the sample plugin in a custom application/pipeline. How do I obtain individual sources after batched inferencing/processing? Please refer to deepstream python documentation, GitHub GitHub - NVIDIA-AI-IOT/deepstream_python_apps: DeepStream SDK Python bindings.
DeepStream - Intelligent Video Analytics Demo | NVIDIA NGC Where can I find the DeepStream sample applications? In order to use docker containers, your host needs to be set up correctly, not all the setup is done in the container. Understand rich and multi-modal real-time sensor data at the edge. Why is that?
Running DeepStream sample apps in docker container Welcome to the NVIDIA DeepStream SDK API Reference.
NvDsAnalyticsMeta Deepstream Deepstream Version: 6.2 documentation IVA is of immense help in smarter spaces. DeepStream applications can be created without coding using the Graph Composer. By performing all the compute heavy operations in a dedicated accelerator, DeepStream can achieve highest performance for video analytic applications. How to fix cannot allocate memory in static TLS block error? Holds the circle parameters to be overlayed. It comes pre-built with an inference plugin to do object detection cascaded by inference plugins to do image classification. 0.1.8. Any use, reproduction, disclosure or distribution of this software and related documentation without an express license agreement from NVIDIA Corporation is strictly prohibited. Also, DeepStream ships with an example to run the popular YOLO models, FasterRCNN, SSD and RetinaNet. The registry failed to perform an operation and reported an error message. DeepStream SDK can be the foundation layer for a number of video analytic solutions like understanding traffic and pedestrians in smart city, health and safety monitoring in hospitals, self-checkout and analytics in retail, detecting component defects at a manufacturing facility and others. Why do I encounter such error while running Deepstream pipeline memory type configured and i/p buffer mismatch ip_surf 0 muxer 3? To learn more about bi-directional capabilities, see the Bidirectional Messaging section in this guide. Learn how the latest features of DeepStream are making it easier than ever to achieve real-time performance, even for complex video AI applications. There are billions of cameras and sensors worldwide, capturing an abundance of data that can be used to generate business insights, unlock process efficiencies, and improve revenue streams. 1. Can Gst-nvinferserver support models across processes or containers?
DeepStream 6.2 is now available for download! - DeepStream SDK - NVIDIA TAO toolkit Integration with DeepStream. Unable to start the composer in deepstream development docker. Deploy AI services in cloud native containers and orchestrate them using Kubernetes. It delivers key benefits including validation and integration for NVIDIA AI open-source software, and access to AI solution workflows to accelerate time to production.
Drivers - Nvidia How to enable TensorRT optimization for Tensorflow and ONNX models? NvOSD. 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, 4.1 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, 5.1 nvmultiurisrcbin config recommendations and notes on expected behavior, 3.1 Gst Properties to configure nvurisrcbin, You are migrating from DeepStream 6.0 to DeepStream 6.2, Application fails to run when the neural network is changed, The DeepStream application is running slowly (Jetson only), The DeepStream application is running slowly, 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, Frequent tracking ID changes although no nearby objects, Frequent tracking ID switches to the nearby objects, Error while running ONNX / Explicit batch dimension networks, My component is not visible in the composer even after registering the extension with registry. DeepStream is an integral part of NVIDIA Metropolis, the platform for building end-to-end services and solutions that transform pixels and sensor data into actionable insights. Developers can now create stream processing pipelines that incorporate neural networks and other complex processing tasks such as tracking, video encoding/decoding, and video rendering. This helps ensure that your business-critical projects stay on track. Where can I find the DeepStream sample applications? How can I verify that CUDA was installed correctly? Can Gst-nvinferserver support inference on multiple GPUs?
Bridging Cloud services and AI solutions at the Edge How can I display graphical output remotely over VNC? Mrunalkshirsagar August 4, 2020, 2:59pm #1. NVIDIA introduced Python bindings to help you build high-performance AI applications using Python.
NVIDIA DeepStream SDK API Reference: Main Page | NVIDIA Docs Highlights: Graph Composer. What is the difference between DeepStream classification and Triton classification? What is the difference between batch-size of nvstreammux and nvinfer? DeepStream 5.x applications are fully compatible with DeepStream 6.2. What are different Memory transformations supported on Jetson and dGPU? How to tune GPU memory for Tensorflow models? Why does the RTSP source used in gst-launch pipeline through uridecodebin show blank screen followed by the error -. NVDS_LABEL_INFO_META : metadata type to be set for given label of classifier. What are different Memory types supported on Jetson and dGPU? Graph Composer gives DeepStream developers a powerful, low-code development option. Trifork jumpstarted their AI model development with NVIDIA DeepStream SDK, pretrained models, and TAO Toolkit to develop their AI-based baggage tracking solution for airports. NvBbox_Coords.cast() Some popular use cases are retail analytics, parking management, managing logistics, optical inspection, robotics, and sports analytics. The plugin for decode is called Gst-nvvideo4linux2. User can add its own metadata type NVDS_START_USER_META onwards. Enabling and configuring the sample plugin. How can I run the DeepStream sample application in debug mode? line_width - int, Holds border_width of the . How can I determine the reason? NvOSD_CircleParams. DeepStream provides building blocks in the form of GStreamer plugins that can be used to construct an efficient video analytic pipeline. What types of input streams does DeepStream 6.2 support? Action Recognition. DeepStream abstracts these libraries in DeepStream plugins, making it easy for developers to build video analytic pipelines without having to learn all the individual libraries. How to clean and restart? What is the official DeepStream Docker image and where do I get it? NVDS_CLASSIFIER_META : metadata type to be set for object classifier. New #RTXON The Lord of the Rings: Gollum TM Trailer Released.
Gst-nvinfer DeepStream 6.2 Release documentation - NVIDIA Developer Whether its at a traffic intersection to reduce vehicle congestion, health and safety monitoring at hospitals, surveying retail aisles for better customer satisfaction, or at a manufacturing facility to detect component defects, every application demands reliable, real-time Intelligent Video Analytics (IVA). Can users set different model repos when running multiple Triton models in single process? How can I check GPU and memory utilization on a dGPU system? Power on each server. Reference applications can be used to learn about the features of the DeepStream plug-ins or as templates and starting points for developing custom vision AI applications. Metadata propagation through nvstreammux and nvstreamdemux. To read more about these apps and other sample apps in DeepStream, see the C/C++ Sample Apps Source Details and Python Sample Apps and Bindings Source Details. RTX GPUs performance is only reported for flagship product(s). Get step-by-step instructions for building vision AI pipelines using DeepStream and NVIDIA Jetson or discrete GPUs. Batching is done using the Gst-nvstreammux plugin. And once it happens, container builder may return errors again and again. Optimizing nvstreammux config for low-latency vs Compute, 6. How to get camera calibration parameters for usage in Dewarper plugin? How to find the performance bottleneck in DeepStream? How to find out the maximum number of streams supported on given platform? To learn more about deployment with dockers, see the Docker container chapter. Object tracking is performed using the Gst-nvtracker plugin. Why am I getting following warning when running deepstream app for first time? . How to tune GPU memory for Tensorflow models? DeepStream SDK Python bindings and sample applications - GitHub - NVIDIA-AI-IOT/deepstream_python_apps: DeepStream SDK Python bindings and sample applications How to clean and restart? There are 4 different methods to install DeepStream proposed in the documentation, the one that I've tested is: Method 2: Using the DeepStream tar . The container is based on the NVIDIA DeepStream container and leverages it's built-in SEnet with resnet18 backend (TRT model which is trained on the KITTI dataset). x2 - int, Holds width of the box in pixels. I started the record with a set duration. How can I determine whether X11 is running? What types of input streams does DeepStream 6.2 support? Its ideal for vision AI developers, software partners, startups, and OEMs building IVA apps and services. Using a simple, intuitive UI, processing pipelines are constructed with drag-and-drop operations. The NvDsBatchMeta structure must already be attached to the Gst Buffers. The data types are all in native C and require a shim layer through PyBindings or NumPy to access them from the Python app. How do I obtain individual sources after batched inferencing/processing? DeepStream 6.2 is now available for download! Learn how NVIDIA DeepStream and Graph Composer make it easier to create vision AI applications for NVIDIA Jetson.
Custom Object Detection with CSI IR Camera on NVIDIA Jetson .
DeepStream + Python Bindings on Jetson. | Medium 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. How can I specify RTSP streaming of DeepStream output? To get started, download the software and review the reference audio and Automatic Speech Recognition (ASR) applications. Ensure you understand how to migrate your DeepStream 6.1 custom models to DeepStream 6.2 before you start. Build high-performance vision AI apps and services using DeepStream SDK. How to fix cannot allocate memory in static TLS block error? My DeepStream performance is lower than expected. What are the sample pipelines for nvstreamdemux? With native integration to NVIDIA Triton Inference Server, you can deploy models in native frameworks such as PyTorch and TensorFlow for inference. DeepStream supports several popular networks out of the box. Then, you optimize and infer the RetinaNet model with TensorRT and NVIDIA DeepStream. Variables: x1 - int, Holds left coordinate of the box in pixels. You can find details regarding regenerating the cache in the Read Me First section of the documentation. The containers are available on NGC, NVIDIA GPU cloud registry. Are multiple parallel records on same source supported? DeepStream builds on top of several NVIDIA libraries from the CUDA-X stack such as CUDA, TensorRT, NVIDIA Triton Inference server and multimedia libraries. Type and Range. Why am I getting following warning when running deepstream app for first time? How can I get more information on why the operation failed? What is the difference between DeepStream classification and Triton classification? It is the release with support for Ubuntu 20.04 LTS. Graph Composer is a low-code development tool that enhances the DeepStream user experience. On Jetson platform, I get same output when multiple Jpeg images are fed to nvv4l2decoder using multifilesrc plugin. At the bottom are the different hardware engines that are utilized throughout the application. mp4, mkv), DeepStream plugins failing to load without DISPLAY variable set when launching DS dockers, On Jetson, observing error : gstnvarguscamerasrc.cpp, execute:751 No cameras available. Running without an X server (applicable for applications supporting RTSP streaming output), DeepStream Triton Inference Server Usage Guidelines, Creating custom DeepStream docker for dGPU using DeepStreamSDK package, Creating custom DeepStream docker for Jetson using DeepStreamSDK package, Recommended Minimal L4T Setup necessary to run the new docker images on Jetson, Python Sample Apps and Bindings Source Details, Python Bindings and Application Development, DeepStream Reference Application - deepstream-app, Expected Output for the DeepStream Reference Application (deepstream-app), DeepStream Reference Application - deepstream-test5 app, IoT Protocols supported and cloud configuration, 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, Using Easy-NMOS for NMOS Registry and Controller, 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, 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, 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), Sensor provisioning with deepstream-test5-app, Callback implementation for REST API endpoints, DeepStream 3D Action Recognition App Configuration Specifications, Custom sequence preprocess lib user settings, Build Custom sequence preprocess lib and application From Source, Depth Color Capture to 2D Rendering Pipeline Overview, Depth Color Capture to 3D Point Cloud Processing and Rendering, 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, DS3D Custom Components Configuration Specifications, Lidar Point Cloud to 3D Point Cloud Processing and Rendering, 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, Networked Media Open Specifications (NMOS) in DeepStream, DeepStream Can Orientation App Configuration Specifications, Application Migration to DeepStream 6.2 from DeepStream 6.1, Running DeepStream 6.1 compiled Apps in DeepStream 6.2, Compiling DeepStream 6.1 Apps in DeepStream 6.2, 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 Configuration File Specifications, Tensor Metadata Output for Downstream Plugins, NvDsTracker API for Low-Level Tracker Library, Unified Tracker Architecture for Composable Multi-Object Tracker, Low-Level Tracker Comparisons and Tradeoffs, Setup and Visualization of Tracker Sample Pipelines, How to Implement a Custom Low-Level Tracker Library, NvStreamMux Tuning Solutions for specific use cases, 3.1.