TechnologiesMachine Learning & AI

CreateML

iOSmacOStvOSwatchOSvisionOS

CreateML trains and evaluates custom Core ML models directly on device, spanning classifiers, regressors, and image, text, sound, and tabular tasks. You load and shape training data with MLDataTable, MLDataColumn, and MLDataValue, then fit models such as MLImageClassifier, MLSoundClassifier, MLObjectDetector, MLRecommender, MLLinearRegressor, or tree-based estimators like MLBoostedTreeClassifier and MLRandomForestRegressor. Training results are assessed through metrics types including MLClassifierMetrics, MLRegressorMetrics, and MLObjectDetectorMetrics, while MLJob, MLProgress, MLPhase, and MLCheckpoint let you monitor and manage long-running training sessions. Specialized estimators such as MLActionClassifier, MLHandPoseClassifier, MLStyleTransfer, and MLGazetteer cover action recognition, pose, image styling, and named-entity tasks.

Training Data 6

Load, shape, and represent the tabular data you use to train and evaluate models.

  • St
    MLDataTableiOS 15.0+
    A table of data for training or evaluating a machine learning model.
  • St
    MLDataColumniOS 15.0+
    A column of typed values in a data table.
  • St
    MLUntypedColumniOS 15.0+
    A column of untyped values in a data table.
  • En
    MLDataValueiOS 15.0+
    The value of a cell in a data table.
  • Pr
    MLDataValueConvertibleiOS 15.0+
    A type that can convert itself to and from a data value.
  • En
    MLSplitStrategyiOS 15.0+
    Data partitioning approaches, typically for creating a validation dataset

Image Models 3

Estimators that train Core ML models for image classification, object detection, and image styling.

  • St
    MLImageClassifier
    A model you train to classify images.
  • St
    MLObjectDetector
    A model you train to classify one or more objects within an image.
  • St
    MLStyleTransfer
    A model you train to apply an image’s style to other images or videos.

Sound and Motion Models 5

Estimators that train models recognizing sounds, activities, and hand-based actions or poses.

  • St
    MLSoundClassifier
    A machine learning model you train with audio files to recognize and identify sounds on a device.
  • St
    MLActionClassifier
    A model you train with videos to classify a person’s body movements.
  • St
    MLActivityClassifier
    A model you train to classify motion sensor data.
  • St
    MLHandActionClassifier
    A task that creates a hand action classification model by training with
  • St
    MLHandPoseClassifier
    A task that creates a hand pose classification model by training with images

Text and Language Models 4

Estimators that train models for text classification, named-entity tagging, and word representation.

  • St
    MLTextClassifier
    A model you train to classify natural language text.
  • St
    MLWordTagger
    A word-tagging model you train to classify natural language text at the word level.
  • St
    MLWordEmbedding
    A map of strings in a vector space that enable your app to find similar
  • St
    MLGazetteer
    A collection of terms and their labels, which augments a tagger that analyzes natural language text.

Tabular Classifiers and Regressors 11

General-purpose classifier and regressor estimators that learn from tabular feature data.

  • St
    MLBoostedTreeClassifieriOS 15.0+
    A classifier based on a collection of decision trees combined with gradient boosting.
  • St
    MLBoostedTreeRegressoriOS 15.0+
    A regressor based on a collection of decision trees combined with gradient boosting.
  • St
    MLDecisionTreeClassifieriOS 15.0+
    A classifier that predicts the target by creating rules to split the data.
  • St
    MLDecisionTreeRegressoriOS 15.0+
    A regressor that estimates the target by learning rules to split the data.
  • St
    MLRandomForestClassifieriOS 15.0+
    A classifier based on a collection of decision trees trained on subsets of the data.
  • St
    MLRandomForestRegressoriOS 15.0+
    A regressor based on a collection of decision trees trained on subsets of the data.
  • St
    MLLinearRegressoriOS 15.0+
    A regressor that estimates the target as a linear function of the features.
  • St
    MLLogisticRegressionClassifieriOS 15.0+
    A classifier that predicts a discrete target value as a function of data features.
  • St
    MLSupportVectorClassifier
    A classifier that predicts a binary target value by maximizing the separation between categories.
  • En
    MLClassifier
    A model you train to classify data into discrete categories.
  • En
    MLRegressor
    A model you train to estimate continuous values.

Recommendation 1

An estimator that trains a model to recommend items from interaction data.

  • St
    MLRecommender
    A model you train to make recommendations based on item similarity,

Evaluation Metrics 5

Types that report a trained model's accuracy and performance on validation or test data.

  • St
    MLClassifierMetricsiOS 15.0+
    Metrics you use to evaluate a classifier’s performance.
  • St
    MLRegressorMetricsiOS 15.0+
    Metrics you use to evaluate a regressor’s performance.
  • St
    MLObjectDetectorMetrics
    Metrics you use to evaluate an object detector’s performance.
  • St
    MLRecommenderMetrics
    Metrics you use to evaluate a recommender’s performance.
  • St
    MLWordTaggerMetrics
    Metrics you use to evaluate a word tagger’s performance.

Training Sessions and Progress 9

Manage, monitor, checkpoint, and visualize long-running asynchronous training sessions.

  • Cl
    MLJobiOS 15.0+
    The representation of a model’s asynchronous training session you use to
  • Cl
    MLTrainingSessioniOS 15.0+
    The current state of a model’s asynchronous training session.
  • St
    MLTrainingSessionParametersiOS 15.0+
    The configuration settings for a training session.
  • St
    MLCheckpointiOS 15.0+
    The state of a model’s asynchronous training session at a specific point in
  • St
    MLProgressiOS 15.0+
    A convenience type that exposes information about the progress of a training
  • En
    MLPhaseiOS 15.0+
    The possible states of a training session.
  • Pr
    MLVisualizable
    An image visualization of machine learning types.
  • Pr
    MLStreamingVisualizable
    A sequence of image visualizations for machine learning types.
  • Pr
    MLIdentifier
    A type the Create ML framework can use as a machine learning identifier.

Model Metadata 1

Author-supplied information attached to a trained Core ML model.

  • St
    MLModelMetadataiOS 15.0+
    Information about a model that’s stored in a Core ML model file.

Bounding Box Configuration 3

Constants describing how object-detection bounding boxes are anchored, oriented, and measured.

  • En
    MLBoundingBoxAnchor
    A location within a bounding box that an annotation’s coordinates use as
  • En
    MLBoundingBoxCoordinatesOrigin
    The location within an image that an annotation’s coordinates use as their
  • En
    MLBoundingBoxUnits
    The units a bounding box annotation uses to define its position and size.

Errors 1

Errors that can occur while creating or training a model.

  • En
    MLCreateErroriOS 15.0+
    The errors Create ML throws while performing various operations, such as

Extends 9

IntStringArrayInt32FloatDoubleDictionaryBoolInt64
← Machine Learning & AI