NVIDIA has released a new version of DeepStream, part of the chip giant’s NVIDIA Metropolis AI platform for smart cities.
The NVIDIA DeepStream Software Development Kit (SDK) was originally released in 2017 to simplify the deployment of scalable intelligent video analytics (IVA) powered by deep learning. Developers can use DeepStream to process, understand and categorize video frames in real time and within stringent throughput and latency requirements.
DeepStream SDK 2.0 Early Access offers the following development tools:
- Parallel Multi-Stream Processing: Creating high-stream density applications with deep learning and accelerated multimedia image processing to build solutions at scale.
- Heterogeneous Concurrent Neural Network Architecture: Leveraging multiple neural networks to process each video stream, accommodating different deep learning techniques for more intelligent insights.
- Configurable Processing Pipelines: Easily creating flexible and intuitive graph-based applications, resulting in highly optimized pipelines delivering maximum throughput.
NVIDIA believes the new release will help simplify developers’ AI integration processes: “Rather than designing an end-to-end solution from scratch, DeepStream comes with plug-ins, sample applications, and pre-trained deep learning model examples. This makes it the most effective way to develop and deploy advanced AI for complex video analytics.”
NVIDIA DeepStream SDK 2.0 is available for Tesla GPUs including Tesla P4 and P40, and can be downloaded at: https://developer.nvidia.com/deepstream-sdk?ncid=so-blo-dmsk20ntllh-43601
Author: Mos Zhang | Editor: Michael Sarazen