With the amount of continuously generated data on the rise, the cost to upload and store that data in the cloud is increasing. Data is being gathered faster than it is stored and immediate action is often required. Sending all the data to the cloud can result in latency and presents risks when internet connectivity is intermittent. Edge computing involves processing data locally for immediate...
To help grow deep learning inference applications at the edge, Intel developed the energy efficient and low cost Intel® Movidius™ Neural Compute Stick - a tiny fanless deep learning device powered by the Intel® Movidius™ Vision Processing Unit (VPU).
The tutorial includes instructions for deploying deep learning recognition models to Microsoft Azure*.
1. Robots and ASTRO