Create ML | Core ML | The Ultimate Swift 5 IOS Course

Install Create ML on your Mac by downloading Xcode from the App Store, signing in with an Apple ID, and selecting Create ML, then open new documents to browse templates.

Explore image classifiers by preparing data, training models, and testing them to build an x-ray classifier that distinguishes hip, chest, hand, and leg x-rays.

Discover how to efficiently gather and download x-ray image datasets for your classifier using a chromium-based browser extension, then clean and prepare the data for Create ML.

Filter images to png/jpeg/gif, organize a dataset, and use Create ML with Roboflow to generate train, validation, and test sets with augmentations.

Train and test an image classifier with Create ML on a prepped x-ray dataset, monitor training and validation accuracy, and export a Core ML model for iOS.

Learn to build a live capture iOS app that integrates an X-ray classifier Core ML model, processes camera frames, and displays real-time classification results with scale-fit image handling.

Run and test the classifier in the iOS app with a live demo on a physical device, recognizing hip, chest, knee, and hand x-rays.

Learn how object detection locates items in images with bounding boxes, create and label custom datasets in Create ML, and prepare x-ray object detection projects.

Create an object detection project in Roboflow, label hip x-ray images with bounding boxes along the inter teardrop line, and prepare data for Create ML.

Train object detection models using the phone network or transfer learning, set iterations and batch size, adjust grid size, and monitor loss toward convergence with snapshots and previews.

Integrate an object detection model into an iOS app, test live object recognition with Vision, and draw a line from the left to the right detected teardrop, showcasing real-time results.

Apply mosaic style transfer to images and videos by training a model with a template image and content images, adjusting style strength and density to balance style and content.

Train a cat-and-dog sound classifier using an audio feature extractor (audio feature print or vggish), tune window overlap, and export the model as cat and dog sound classifier.ml.

Integrate a sound classifier into iOS app, wiring wave view, a record button, and an output label to show cat or dog predictions with confidence from the ml model.

Create a movie recommendation model based on user preferences, trained with MovieLens data via Create ML, and tested with 25 million and 1 million ratings to emulate Netflix-style suggestions.

Export and add the movie recommender.ml model into a new iOS app, build a simple UI with movie id and rating, and display ten recommendations.

Explore tabular classification using the iris dataset to predict species, train with csv data, compare algorithms like decision trees, random forest, boosted trees, svm, and logistic regression, and evaluate results.

Create an iOS app that integrates a tabular iris classifier using Core ML, wiring sliders for sepal and petal measurements to a predict button and result label.

Learn tabular regression by predicting red wine quality from a CSV dataset using Create ML in Xcode, with training, validation, and testing data and multiple regression algorithms.

Integrate the wine quality regressor into an iOS app with Core ML by building a new project, importing the model, and implementing a predict function to output quality.

Learn text classification and sentiment analysis with create ml, including preparing csv to json data, labeling text, and training with maximum entropy or CRF before testing.

Learn to integrate a text classifier into a mobile app using Core ML and natural language, creating an airline sentiment analysis tool with a predict function and a user interface.