A structure that describes additional model parameters that you can set on the sound classifier.
SDKs
- macOS 10.14+
- Xcode 11.0+
Framework
- Create ML
Declaration
struct MLSound Classifier.ModelParameters
A structure that describes additional model parameters that you can set on the sound classifier.
SDKs
Framework
struct MLSound Classifier.ModelParameters
init(validation Data: [String : [URL]]?, max Iterations: Int, overlap Factor: Double)
Creates a new instance of MLSound
.
init(validation Data: MLSound Classifier .Data Source, max Iterations: Int, overlap Factor: Double)
Creates a new instance of MLSound
.
var max Iterations: Int
The maximum number of training iterations to perform.
var overlap Factor: Double
The percentage of overlap between two consecutive audio analysis windows when generating training data.
var description: String
A string representation of the model parameters.
var debug Description: String
A string representation of the model parameters that’s suitable for output during debugging.
var playground Description: Any
A description of the parameters shown in a playground.
init(training Data: [String : [URL]], parameters: MLSound Classifier .Model Parameters)
Creates a sound classifier from a training data set represented by a dictionary.
init(training Data: MLSound Classifier .Data Source, parameters: MLSound Classifier .Model Parameters)
Creates a sound classifier from a training data set represented by a data source.
enum MLSound Classifier .Data Source
An enumeration that describes various ways to label audio-file URLs stored on disk.
let model Parameters: MLSound Classifier .Model Parameters
The configuration parameters used to train the model during initialization.