Intel® AI Academy | All Courses

AI on the Edge with Computer Vision

Summary

This course provides a complete introduction on how to use the Intel® Movidius™ Neural Compute Stick (NCS) for low-power deep learning inference on edge devices. Topics covered include:

  • How to install and use the Intel® Movidius™ Neural Compute SDK (NCSDK)
  • The basics of deep learning vision applications and model topologies
  • How to create computer vision applications in Python* using Intel® Movidius™ Neural Compute Stick devices

By the end of this course, students will have practical knowledge of how to use the Intel Movidius NCS to:

  • Analyze model performance with the included performance tools
  • Deploy pretrained networks and custom networks on the Intel Movidius NCS
  • Run low-power distributed inference with multiple Intel Movidius NCS devices and multiple networks

The course is structured around six weeks of lectures and exercises. Each week requires three hours to complete. The code examples are implemented in Python*, so familiarity with the language is encouraged (you can learn along the way).

Prerequisites

Python* programming
Calculus
Linear algebra

Hardware Required:

Intel Movidius Neural Compute Stick

Raspberry Pi* 3 Model B

 

For Professors: Request Free Access to Curriculum

Week 1

This class introduces the Intel® Movidius™ Neural Compute Stick. Topics include:

  • A comparison of the differences between traditional computer vision and deep learning
  • A review of the Intel® AI Portfolio including hardware and tools
  • How to use the Intel Movidius NCS and NCSDK

Download

Week 2

This class teaches a basic example of how to create an image classifier application. Learn how to: 

  • Identify an image classifier and determine what model topologies are used
  • Export trained models from Caffe* and TensorFlow*
  • Use the API and product graph file in the Intel Movidius NCSDK

Download

Week 3

This class shows an example of how to profile classifiers and choose which works for your application. Topics include:

  • How to use the performance analysis tool
  • The comparison of pretrained models and the ImageNet* ILSVRC dataset
  • Ways to optimize performance and other benefits

Download

Week 4

This class shows how to deploy a custom convolutional neural network using the Intel Movidius NCSDK:

  • Learn how to prepare a dataset and train a neural network
  • Analyze the results after training, and then fine-tune your network before deploying to the Intel Movidius NCS

Download

Week 5

This class show you how to use the Intel Movidius NCS to:

  • Use object detection in still images and a live camera feed
  • Create a prototype smart security camera with Raspberry Pi*

Download

Week 6

This week, learn how to implement deep neural network image processing systems on low-power devices. In addition, learn:

  • How to install the Intel Movidius NCSDK on a Raspberry Pi in an API-only mode
  • How to deploy models to multiple Intel Movidius NCS devices

Download