ML and AI Resources in iOS
A directory of my iOS tutorials related to CoreML, Vision, RealityKit, and other frameworks
Here’s a list of my mobile ML in iOS resources posted on Better Programming:
Machine Learning — Core ML, Create ML, and Natural Language
Core ML 3 On Device Training — Part 1: Build Updatable Model, Part 2: Re-train On Device — What if a cat vs. dog image classification model gave incorrect results? This tutorial shows how to re-train and update the model on your device with the correct data. Was published in 2019, so might require an updated
PencilKit Meets Core ML — Recognizing digits from drawing using MNIST
Build a Core ML Movie Recommender SwiftUI App Using Create ML — Leverage CreateML’s recommender template to predict the top K movie recommendations based on user ratings in a SwiftUI application
Sound Classifier Using Core ML and Create ML — Recognize by voice in a live audio stream using the SoundAnalysis framework with your own Core ML model built using Create ML
Classify Movie Reviews Using Natural Language Framework — By using built-in sentiment analysis and NLP’s Text classification on the Rotten Tomatoes dataset.
Sentiment Analysis of Hacker News feed — Using Apple’s built-in sentiment score for NLP, we see that most top stories attract polarizing opinions on Hacker News.
Build a SwiftUI + Core ML Emoji Hunt Game for iOS — Let’s create a fun machine-learning iOS camera app that lets you search for things in your house that are similar to emojis
Core ML Background Removal — Use the DeepLabV3 image segmentation model to add, remove, and modify image backgrounds in your iOS app
Computer Vision — Core Image and Vision Framework
Image Similarity Using Feature Prints — Determine the Euclidean distance between images using their feature prints
Cropping Areas Of Interest using Saliency — Extract salient features using the upgraded Vision framework
Determine the Best Facial Expression in Live Photos — Using the
Coin Detection —Simplify the contours by leveraging Core Image filters for pre-processing the images before passing them on to the Vision request. We’ll look to mask the images in order to reduce texture noise
Swipeless Tinder Using Hand Pose Estimation — Detect hand gestures to swipe 👍 👎
Person Segmentation — Separate people from backgrounds in images and videos
Anomaly Detection and Watermark Extraction Using Core Image — Use a Core Image filter to find differences and anomalies between images
Entities, Gestures, and Ray Casting — Leveraging Vision and PencilKit frameworks.