Level Topic Type
100 Introduction to computer vision Article
101 Introduction to PowerAI Vision Article
201 Build and deploy a PowerAI Vision model and use it in an iOS app Tutorial
202 Locate and count items with object detection Code pattern
203 Object tracking in video with OpenCV and Deep Learning Code pattern
301 Validate computer vision deep learning models Code pattern

This learning path is designed for developers interested in quickly getting up to speed on what PowerAI Vision offers and how to use it. The learning path consists of step-by-step tutorials, deep-dive videos, and complete examples of working code. As you proceed through the learning path, you will learn about more advanced features as well as different use cases for PowerAI Vision.

To get started, click on a card below, or see the table above for a complete list of topics covered.

Intro to computer vision

Learn about:

  • Image classification
  • Object detection
  • Object tracking in videos
  • Creating custom models
  • Using your model
  • Example use cases

Introduction to PowerAI Vision

Learn about:

  • Creating a data set
  • Assigning categories for image classification
  • Labeling objects for object detection
  • Training a model
  • Testing the model
  • Using it in an app

Build and deploy a PowerAI Vision model and use it in an iOS app

Learn about:

  • Creating a data set
  • Training a model for image classification
  • Deploying it to a web API
  • Integrating the API into an iOS app

Locate and count items with object detection

Learn about:

  • Creating a data set
  • Training a model for object detection
  • Deploying it to a web API
  • Testing the model with REST calls
  • Integrating object detection into a Node.js web app

Object tracking in video with OpenCV and deep learning

Learn about:

  • Using automatic labeling to create an object detection classifier from a video
  • Processing frames of a video using a Jupyter Notebook, OpenCV, and PowerAI Vision
  • Detecting objects in video frames with PowerAI Vision
  • Tracking objects from frame to frame with OpenCV
  • Counting objects in motion as they enter a region of interest
  • Annotating a video with bounding boxes, labels, and statistics

Validate computer vision deep learning models

Learn about:

  • Classifing images using an existing model and a Jupyter Notebook
  • Collecting statistics to evaluate a model
  • Visualizing model accuracy with a confusion matrix
  • Producing a variety of accuracy measure for model validation


Next: Introduction to computer vision