NVIDIA Clara™ Holoscan is the AI computing platform for medical devices 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 consists of:
Enabling medical device developers to create the next-generation of AI-enabled medical devices and take it to the market using a medical grade platform.
Collection of tools to help measure performance of the Holoscan platform (software and hardware).
Visit the NVIDIA Developer Page to learn more about Clara Holoscan and get started today.
The Clara Holoscan Sample Applications container is the simplest way to run the sample applications as it includes all necessary binaries and datasets, and allows for some customization of the application graph and its parameters. The container's architecture is
linux/arm64 as it is designed to run on the Clara Developer Kits.
Refer to the overview of the container on NGC for prerequisites, setup, and run instructions.
Note: The sample applications container does not include build dependencies to update or generate new extensions, or to build new applications with other extensions. This can be done from source instead.
Whether running from source or from a container runtime, the sample applications will need the following AI models and video source datasets:
Note: These two datasets are included in the run container. Refer to the instructions in the source repository to use them when building from source.
GXF is used as a backend to define the graph components, connect them, and execute the applications, see the User Guide for more details.
Note: You do not need to manually download thoses resources as they are encapsulated in the run containers, or downloaded automatically when building from source.