On 16 April 2021 the Swift Heroes Digital 2021 conference was held in virtual format to accomodate the COVID-19 pandemic. Giovanni, Tiago and Moritz were speakers at the conference and presented a workshop on Apple's machine learning technologies, called "Creating Machine Learning Models with Create ML".
The workshop introduced the machine learning frameworks Core ML and the top level APIs Vision, Natural Language, Speech and Sound Analysis. Then the Create ML framework and tool was presented to create a custom object detection machine learning model in a live demo. The workshop concluded with tips and best practices and provided links to additional resources and some boiler plate code sample to use Core ML machine learning models in Swift Playgrounds.
The links to all resources can be found in this Gitlab Snippet. If you are interested in more information about our workshop and what we think are key skills for great iOS developers, consider our interview that was done prior the Swift Heroes Digital 2021 conference.
"Especially with the latest generation of Apple hardware and their dedicated silicon, these technologies deliver fast performance with easy integration, allowing you to build apps with machine learning models with just a few lines of code. Even without an extensive background in artificial intelligence or mathematics you can supercharge your iPhone, iPad, Apple Watch and Mac apps and make them smarter than ever before."
In addition to providing links to more information, we also created a series of posts to share the content of the workshop in a more concise format that may help you to get started with machine learning technologies in your development projects for Apple platforms.
Using machine learning models with Core ML
In this series we introduce the Core ML framework, its capabitilities and extensive feature set that eveolved over the years. Additionally, in some practical and hands-on tutorials, we share how to use image classification and object detection machine laerning models in Swift Playgrounds or an iOS app.
- Core ML Explained: Apple's Machine Learning Framework
- Using an Image Classification Machine Learning Model in Swift Playgrounds
- Using an Image Classification Machine Learning Model in an iOS App with SwiftUI
- Using an Object Detection Machine Learning Model in Swift Playgrounds
- Using an Object Detection Machine Learning Model in an iOS App
- UIImage+Resize: Resizing an UIImage
- UIImage+CVPixelBuffer: Converting an UIImage to a Core Video Pixel Buffer
Creating machine learning models with Create ML
In this series we introcue the Create ML framework and toolchain to build and train custom machine learning models on your Mac or even on device. Additionally, in some practical and hands-on tutorials, we share how to create datasets of annotated images to create an object detection machine learning model in Create ML.
- Create ML Explained: Apple's Toolchain to Build and Train Machine Learning Models
- Creating an Object Detection Machine Learning Model with Create ML
- Creating annotated data sets with IBM Cloud Annotations
This article is part of a series of articles derived from the presentation Creating Machine Learning Models with Create ML presented as a one time event at the Swift Heroes 2021 Digital Conference on April 16th, 2021.