VPU

This design clusters multiple Intel® Movidius™ Vision Processing Units (VPU) (1~N) on an add-on card or rack-mount module server to provide deep learning inference acceleration. This family of vision accelerator design products comes in multiple form factors to cater to a wide range of vertical use cases.

Common uses:

• Optimization of the video analysis pipeline that includes video codec, image processing, computer vision, and neural network inference

• Real-time, low-latency inference

• Offload capability for high-density, deep-learning inference workloads

Works best for:

• Data center

• Cloud server, edge server, and edge network video recorder (NVR) server for surveillance

Resources:

• Solution Brief

• Performance Benchmarks

Supported hardware:

• Intel® Vision Accelerator Design with Intel® Movidius™ Vision Processing Units (VPU)

Supported operating systems:

• Ubuntu 16.04.3 LTS (64 bit)

• Windows® 10 Enterprise (64 bit)

Supported component:

• Deep Learning Deployment Toolkit