Contents

makeTrainingSession(trainingData:annotationType:parameters:sessionParameters:)

Creates an asynchronous object-detector training session.

Declaration

static func makeTrainingSession(trainingData: MLObjectDetector.DataSource, annotationType: MLObjectDetector.AnnotationType, parameters: MLObjectDetector.ModelParameters = ModelParameters(), sessionParameters: MLTrainingSessionParameters = __Defaults.sessionParameters) throws -> MLTrainingSession<MLObjectDetector>

Parameters

  • trainingData:

    The annotated images the task uses to train the object detector.

  • annotationType:

    The format type of the image annotations in the data source.

  • parameters:

    An Modelparameters Swift.struct instance you use to set the model configuration settings for the training session.

  • sessionParameters:

    An Mltrainingsessionparameters instance you use to configure the training session.

Return Value

An MLTrainingSession that represents the object-detector training session.

Discussion

Use resume(_:) to start the MLTrainingSession instance you get from this method.

See Also

Training an object detector asynchronously