Hands-On Session-

How to use Edge Computing on Real-Time Applications

What is Edge Computing?

  • The new era of IoT(Internet of Things) the number of devices connected to the web is increasing by the million.
  • The existence of such devices demands cloud-based services for data collection. But there is a higher need to get the data centers closer to the devices.

Machine Learning Models for the Edge

 

Some Considerations for Running Models on the Pi

 

  1. Memory Requirements
  2. Larger and more complicated models will require more memory
  3. Model Loading Time
  4. Models that require more memory will take a longer time to load
  5. Inference Time
  6. If your models take a long time for inference, then you might as well stick to the cloud

MobileNets

  • Uses two global hyperparameters
  • Helps to carry out tasks in a timely fashion on a computationally limited platform
  • It has a low latency model
  • It is built primarily from depthwise separable convolutions initially introduced and then which are subsequently used in the Inception Model
Made with Slides.com