Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Lesson 17 – Running AI models on the edge #24

Closed
10 of 11 tasks
jimbobbennett opened this issue May 25, 2021 · 0 comments
Closed
10 of 11 tasks

Lesson 17 – Running AI models on the edge #24

jimbobbennett opened this issue May 25, 2021 · 0 comments
Labels
factory processing The factory processing project lesson

Comments

@jimbobbennett
Copy link
Contributor

jimbobbennett commented May 25, 2021 •
edited by jenfoxbot

Lesson

Concepts taught

  • AI models can be run on the edge – so running on IoT devices closer to the sensors.
  • This is faster, private and can be cheaper.

Learning objectives

  • Learn about the upsides to running IoT models on the edge such as privacy and speed.
  • Learn the downside of running IoT models on the edge such as resiliency and having to manually capture data to retrain the model.
  • Learn how to run the custom vision model on the edge with IoT Edge (either on a Pi, or on your device)

Hardware required

  • Wio/Pi
  • Grove camera sensor or Pi camera
  • Fruit

Software/services

  • VS Code
  • PlatformIO (Wio)
  • IoT Hub (free tier)
  • Custom Vision
  • Cognitive services resource (free tier)

Code

  • On-device code to capture an image from the camera and send it to the custom vision API running on the edge.

Tasks

  • Write lesson
  • Build and test lab - IoT Hub setup with the CLI
  • Build and test lab - IoT Edge setup with the CLI
  • Build and test lab - Local IoT Edge deployment
  • Build and test lab - Raspberry Pi IoT Edge deployment
  • Build and test lab - Wio Terminal
  • Build and test lab - Wio Terminal
  • Build and test lab - Raspberry Pi
  • Build and test lab - Virtual IoT device
  • Pre and post quiz questions
  • Sketchnote
@jimbobbennett jimbobbennett added lesson factory processing The factory processing project labels May 25, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
factory processing The factory processing project lesson
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@jimbobbennett