Create ML
Experience an entirely new way of training machine learning models on your Mac. Create ML takes the complexity out of model training while producing powerful Core ML models.
Experience an entirely new way of training machine learning models on your Mac. Create ML takes the complexity out of model training while producing powerful Core ML models.
Use object tracking, the first spatial computing template, designed to help you track real world objects in your visionOS app. Enhance your customized model training workflow with the new data preview functionality in the Create ML app, and new Swift APIs from Create ML Components that help you create time series models right from within your app.
Train multiple models using different datasets, all in a single project.
Pause, save, resume, and extend your training process.
Visualize and inspect your data to identify issues such as wrongly labelled images, misplaced object annotations.
Train models blazingly fast right on your Mac while taking advantage of CPU and GPU.
Preview your model performance using Continuity with your iPhone camera and microphone on your Mac, or drop in sample data.
Interactively learn how your model performs on test data from your evaluation set. Explore key metrics and their connections to specific examples to help identify challenging use cases, further investments in data collection, and opportunities to help improve model quality.
Create ML has a variety of model types to choose from. Just select a model type in the app and add your data and parameters to start training.
Image classification
Object detection
Hand pose classification
Style transfer
Action classification
Hand action classification
Style transfer
Object Tracking
Activity classification
Sound classification
Text classification
Word tagging
Tabular classification
Tabular regression
Recommendation
The power of Create ML is also available as Swift frameworks on iOS, iPadOS, macOS, tvOS, visionOS, and watchOS. Programmatically experiment and automate model creation in Swift scripts or playgrounds. Build dynamic features that leverage Create ML APIs to train models directly from within your app, providing personalized and adaptive experiences while preserving user privacy.