NVIDIA Holoscan

NVIDIA Holoscan is the AI sensor processing platform that combines hardware systems for low-latency sensor and network connectivity, optimized libraries for data processing and AI, and core microservices to run streaming, imaging, and other applications, from embedded to edge to cloud. It can be used to build streaming AI pipelines for a variety of domains, including Medical Devices, High Performance Computing at the Edge, Industrial Inspection and more.

What's in this collection

• Holoscan Container: this container image includes the Holoscan libraries, GXF extensions, headers, example source code, and sample datasets, as well as all the dependencies that were tested with Holoscan. It is the recommended way to run the Holoscan examples, while still allowing you to create your own C++ and Python Holoscan application.

• Holoscan OpenEmbedded Builder: this container image contains runtime dependencies, scripts, and the NVIDIA-proprietary binary packages that are required to build an OpenEmbedded BSP image for NVIDIA Holoscan Developer Kits.

• Application Data: the following AI models and video datasets have been packaged for use with Holoscan:

  • Sample Video Data
  • Sample Data for AI-based Endoscopy Tool Tracking
  • Sample App Data for AI-based Bone Scoliosis Segmentation
  • Sample Data for AI Colonoscopy Segmentation of Polyps
  • Sample Data for Multi-AI Ultrasound Pipeline
  • Sample Data for AI Endoscopy Out of Body Detection
  • Sample Data for AI Endoscopy Depth Estimation
  • Sample Data for SSD Detection for Endoscopy Surgical Tools
  • Sample video data for cars detection
  • Sample data for MONAI Endoscopic Tool Segmentation
  • Sample data for Volume rendering