Advancing AI Applications with Custom GPU-Powered Plugins for NVIDIA DeepStream
, Global Developer Relations Manager, NVIDIA
Unlock the power of computer vision with innovative (and accessible) tools like NVIDIA DeepStream SDK for image processing and NVIDIA’s specialized computer vision library, CV-CUDA. With these powerful tools, developers can quickly create highly accurate, custom real-time AI solutions in a fraction of the time that traditional methods would require.
We’ll be showcasing the recently announced (and available for early access) NVIDIA CV-CUDA, an open-source project that enables building efficient cloud-scale Artificial Intelligence (AI) imaging and computer vision (CV) applications using GPU processing.
In this session we will demonstrate step-by-step how to build a custom plug-in for DeepStream using the CV-CUDA library to accelerate a vision ai pipeline from end to end.
If you’re new to NVIDIA DeepStream, we recommend taking the 101 prerequisite: An Intro into NVIDIA DeepStream and AI-streaming Software Tools.