Clara Deploy SDK is being consolidated into Clara Holoscan SDK

More info https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/collections/claradeploy

Clara Render Service

This asset requires the Clara Deploy SDK. Follow the instructions on the Clara Ansible page to install the Clara Deploy SDK.

Overview

The Clara Render Service provides realistic visualization of 3D medical data.

Clients connect to the server using a gRPC interface. The 3D medical image data and properties defining how to render the data are provided by the client. The server then provides a video stream of the visualized data.

This container works with the Clara Render Dataset Service and Clara Dashboard to manage data sets and visualize data on the web browser.

Running the Clara Render Service

Before running the container, use docker pull to ensure an up-to-date image is installed. Once the pull is complete, you can run the container image.

Procedure

1. In the Tags section, locate the container image release that you want to run.
2. In the PULL TAG column in the table, click the icon to copy the docker pull command.
3. Open a command prompt and paste the pull command. Ensure the pull completes successfully before proceeding to the next step.
4. Run the Render Service as follows:

# Export some configurations
export ARGS_SERVICE_RSNG_PORT=2050 # Port number of Render Service

nvidia-docker run -it --rm -d \
--name renderserver \
-p ${ARGS_SERVICE_RSNG_PORT:-2050}:2050 \
nvcr.io/nvstaging/clara/renderserver_ng:

Where:

• -it will keep STDIN open even if not attached and allocate a pseudo-TTY
• --rm will delete the container when finished
• -d enables Detached mode: Containers are run in the background
• --name assigns a name to the container
• -p publishes the container port to the host (here, we use 2050)
• `` is the container version (for example, 0.1.0).

You can also mount a cache folder to /cache for improved performance (e.g., -v /tmp:/cache). Cache folders inside the container are defined by the following environment variables (you can change the value by -e option):

• CUDA_CACHE_PATH=/cache/CudaCache
• OPTIX_CACHE_PATH=/cache/OptixCache

To interact with Render Service, use the Clara Dashboard. 5. Stop the container.

If you want to stop Render Server, use the following command:

docker stop renderserver

License

An End User License Agreement is included with the product. By pulling and using the Clara Deploy asset on NGC, you accept the terms and conditions of these licenses.

Suggested Reading

Release Notes, the Getting Started Guide, and the SDK itself are available at the NVIDIA Developer forum.

For answers to any questions you may have about this release, visit the NVIDIA Devtalk forum.