NVIDIA Clara is a computational platform with SDKs and tools to help you build, manage, and deploy AI into medical imaging workflows and instruments. It consists of two major parts: Clara Train SDK and Clara Deploy SDK.
You can find more information here: https://developer.nvidia.com/clara (including documentation how to integrate Clara into your workflow, what are the requirements and how to do the setup)
As depicted in the Platform Stack figure, Clara can run locally on your GPU (Tesla, Quadro, DGX station) or on the GPUs in the cloud (e.g. DGX1 or DGX2, or any public cloud provider). You don’t have to use all the elements of Clara. Just use the parts of Clara that make most sense for your application! We want to help you augmenting your solution by making it easy to accelerate it on the GPU and provide you tools for AI.
We don’t have a setup video yet, but you can find a setup guide in the documentation.
And here are some additional infos: