Holoscan RidgeRun Operators

🚧 Documentation is under development

The Holoscan SDK guide is currently under active development. Some sections may be incomplete or change without notice.

Questions? Contact RidgeRun or email to support@ridgerun.com.

Holoscan SDK

< >

Contents Pin

• Overview
  • Scope and Release Coverage
  • How Can RidgeRun Help?
  • Holoscan SDK at a Glance
  • Why the API Changed
  • Architecture and Execution Model
• Build, Run, and Validate
  • Build the SDK on AGX Orin
  • Running and Stopping
  • Run SDK Examples
• Core Concepts
  • Operators and Graphs
    • Operator Lifecycle
    • Ports, Samples, and Payload Types
    • Temporal Contracts and Input Selection
    • Building Graphs and Queue Policies
    • Fan-Out, Fan-In, Mux, and Demux
    • Execution Planning and Capacity
      • Automatic Partitioning and Plan Inspection
      • Rates, Queue Sizing, and Derived Tensor Capacity
    • Dynamic Graph Behavior
  • Tensor Data and Memory
    • Tensor Contracts and Memory Types
    • Sensor Payloads and Schemas
    • Allocation Ownership and Tensor Pools
    • Zero-Copy Data Flow and CUDA Stream Ordering
    • Copy Paths and Memory Conversion
    • External Memory: VPI, PVA, NvSci, and DLPack
  • Interprocess Communication
    • Channels and HoloMQ
    • External Endpoints and Endpoint Catalogs
    • Descriptor-Tensor External Topics
    • Standalone ChannelRuntime Clients
    • Dynamic External Peers
• Application and Operator Development
  • Building an HSDK Application
  • Writing a Minimal Operator
  • Typed Parameters and Configuration
  • Reading, Writing, and Forwarding Data
  • Writing Tensor Operators
  • Complete Operator Patterns
  • Authoring Runtime Behavior
  • Runtime Parameter Updates
  • Lifecycle Callbacks and Restart Control
  • Performance and Debugging
  • SDK Source Map
• Operator Reference
  • Core Operators
    • ConvertToOp
    • CopyMakeBorderOp
    • CustomCropOp
    • HolovizOp
    • InferenceOp
    • NonMaximumSuppressionOp
    • NormalizeOp
    • ReformatOp
    • RemapOp
    • ResizeOp
  • Holoscan Camera
    • Overview
    • Build and Installation
    • V4L2CaptureOp
    • SIPLCaptureOp
  • Holoscan RidgeRun
    • Overview
    • Build and Installation
    • ArgusCameraOp
    • V4L2SourceOp
    • V4L2UserPtrSourceOp
    • BgraToPlanarTensorOp
    • RawBayerToBgraOp
    • RawBayerToYoloTensorOp
    • YuyvToBgraOp
    • TensorRtInferenceOp
    • DrmDisplayOp
    • DrmBgraDisplayOp
    • X11DisplayOp
    • CudaCompositorOp
    • DepthColorizerOp
    • FakesinkOp
    • FrameSkipperOp
    • InterprocessSrcOp
    • TestPatternOp
• Migration from Holoscan 4.x
  • Concept Map
  • Applications, Fragments, and Graphs
  • Conditions and Temporal Contracts
  • Code-Level API Evolution
• Examples
  • Core
    • Vision Pipeline Example
    • Managed Run Control Example
    • Automatic Partitioning Example
    • Rate-Aware Ports and Tensor Pool Capacity Example
    • CUDA Green Context Example
    • Inference Example
    • Descriptor-Tensor External Topic Example
    • HoloMQ Example
  • Holoscan Camera
    • SIPL Frame Saver Example
    • SIPL Stereo Monitor Example
  • Holoscan RidgeRun
    • Interprocess External-Endpoint Demo
• Benchmark and Use Cases
  • Holoscan vs GStreamer
    • Overview
    • Capture and Display
      • Execution context
      • G2G latency
      • CPU utilization
      • GPU utilization
      • Process memory (RSS)
      • Results
      • Analysis
    • Capture and Inference
      • Execution context
      • Software interlatency
      • Inference processing time
      • CPU utilization
      • GPU utilization
      • Process memory (RSS)
      • Results
      • Analysis
    • Compare the workloads
    • Implemented Applications
    • Framework Selection
  • Interprocess

Preliminary reference

This reference is preliminary. The set of available operators and HSDK applications, along with their APIs and documented behavior, may change in future releases.

Holoscan RidgeRun Operators

Build and optimize your edge AI solution

Camera capture, model processing, and display need to work together in your application. RidgeRun can create or adapt operators and optimize the data flow between them. Contact RidgeRun to see how we can help build your edge AI application.

This module contains RidgeRun implementations for camera capture, CUDA image processing, TensorRT inference, display, overlays, transport, and graph testing. Use them as starting points for bringing camera data into an application and connecting the processing stages.

Choose a group by your application goal, then open an operator page for its arguments, data contract, usage example, build requirements, and source definitions. The linked examples show complete RidgeRun application paths.

Repository inventory

The groups below connect common application tasks to the available operators.

Your goal	RidgeRun operators
Bring camera frames into CUDA processing	ArgusCameraOp, V4L2SourceOp, V4L2UserPtrSourceOp
Prepare images for a model or display	BgraToPlanarTensorOp, RawBayerToBgraOp, RawBayerToYoloTensorOp, YuyvToBgraOp
Run a model on CUDA tensors	TensorRtInferenceOp
Present processed video	DrmDisplayOp, DrmBgraDisplayOp, X11DisplayOp
Add depth views and overlays	CudaCompositorOp, DepthColorizerOp
Test graphs, manage workload, and connect processes	FakesinkOp, FrameSkipperOp, InterprocessSrcOp, TestPatternOp

Related RidgeRun examples

• Interprocess External-Endpoint Demo shows a complete cross-process graph using RidgeRun sources and sinks.
• Holoscan vs GStreamer provides application-level benchmark context for the headless and display paths.

Holoscan SDK

Back to top ↑ < >