What is Clara Render Server?

The Clara Render Server (RS) provides visualization of medical data.

RS is supporting multiple different rendering algorithms and a platform to allow developers to create their own renderers and plug them into RS.

Input is 3D volume data or 2D image data together with parameters which determine how the data is rendered.

Output is a video stream or single images.

Requirements

In order to run this container, it requires:

• NVIDIA CUDA Driver 410.48 or higher
• NVIDIA GPU is Pascal or newer

This container has been validated on a single GPU in DGX-1V and DGX-1P environments.

Running the Clara Render Server

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. The pulling of the container image begins. Ensure the pull completes successfully before proceeding to the next step.

4. Create input folder that will be mounted to the container in the next steps.

   mkdir -p input
   

5. Create network for Render Server.

   docker network create claranet
   

6. Place 3D volume data to `input/ExposureRenderer/' folder.

   Put a data set (.mhd and .raw files) as a sub folder on input/ExposureRenderer/ (e.g., input/ExposureRenderer/test folder).

7. Run Render Server.

   nvidia-docker run -it --rm -d \
   --name renderserver \
   --network claranet \
   -p 2050:2050 \
   -v `pwd`/input:/app/datasets \
   nvcr.io/nvidia/clara-renderserver:linux-x86-<x.x.x>
   

   Where:

   • -it means keeping STDIN open even if not attached, and allocating a pseudo-TTY
   • --rm will delete the container when finished
   • -d is for Detached mode: Run containers in the background
   • --name is for assigning a name to the container
   • --network is for connecting a container to a network
   • -p is for publishing container's port to host (here, we use 2050)
   • -v is for mounting host folder to container folder
   • <x.x.x> is the container version. For example, 0.1.0.

   Once Render Server is launched, RS detects file changes in input folder periodically, and data set changes are updated in Web UI (http://localhost:2050).

8. Stop container and remove network

   If you want to stop Render Server and remove the network, execute the following commands:

   docker stop renderserver
   docker network rm claranet
   

License

Licenses and model files are available. They can be pulled as part of the procedure described above or available in the SDK. By pulling and using the container, you accept the terms and conditions of these licenses.

Suggested Reading

For Release Notes, Getting Started Guide and SDK, please visit the NVIDIA Developer forum (https://developer.nvidia.com/clara).

Use the NVIDIA Devtalk forum for questions regarding this Release (https://devtalk.nvidia.com/default/board/362/clara-sdk/).