One Logo Pool Ball
X
Github
Discord

System

CreateMLComponents · IOS API REFERENCE

TimeSeriesClassifierConfiguration

struct · iOS 18.0+ · SDK 27.1

struct TimeSeriesClassifierConfiguration

The configuration for a time-series classifier.

Members (17)

get · iOS 18.0+

randomSeed

TypeScript
get randomSeed(): (number) | null
Swift declaration
var randomSeed: Int?

A seed to generate reproducible results from random operations.

set · iOS 18.0+

randomSeed

TypeScript
set randomSeed(value: (number) | null)
Swift declaration
var randomSeed: Int?

A seed to generate reproducible results from random operations.

get · iOS 18.0+

learningRate

TypeScript
get learningRate(): number
Swift declaration
var learningRate: Float

The starting learning rate. Defaults to 0.005.

set · iOS 18.0+

learningRate

TypeScript
set learningRate(value: number)
Swift declaration
var learningRate: Float

The starting learning rate. Defaults to 0.005.

get · iOS 18.0+

maximumIterationCount

TypeScript
get maximumIterationCount(): number
Swift declaration
var maximumIterationCount: Int

The maximum number of allowed passes through the data. More passes over the data can result in a more accurately trained model. Consider increasing this if the training accuracy is low. Defaults to 25. - Note: This parameter is only used by the `fitted` method. When using the `update` method it's up to you to decide when to stop.

set · iOS 18.0+

maximumIterationCount

TypeScript
set maximumIterationCount(value: number)
Swift declaration
var maximumIterationCount: Int

The maximum number of allowed passes through the data. More passes over the data can result in a more accurately trained model. Consider increasing this if the training accuracy is low. Defaults to 25. - Note: This parameter is only used by the `fitted` method. When using the `update` method it's up to you to decide when to stop.

get · iOS 18.0+

maximumSequenceLength

TypeScript
get maximumSequenceLength(): number
Swift declaration
var maximumSequenceLength: Int

The maximum number of samples that can be classified. This configuration parameter is used as the input size when exporting a Core ML model.

set · iOS 18.0+

maximumSequenceLength

TypeScript
set maximumSequenceLength(value: number)
Swift declaration
var maximumSequenceLength: Int

The maximum number of samples that can be classified. This configuration parameter is used as the input size when exporting a Core ML model.

get · iOS 18.0+

minimumSequenceLength

TypeScript
get minimumSequenceLength(): number
Swift declaration
var minimumSequenceLength: Int

The minimum number of samples required to produce a classification. This configuration parameter controls the size of the model. Set it to the largest value that is reasonable for your task. For example if your input is accelerometer data sampled at 100Hz and you want to recognize actions, the minimum action duration may be one second, so the minimum sequence length is `100Hz * 1s = 100`. Defaults to 100.

set · iOS 18.0+

minimumSequenceLength

TypeScript
set minimumSequenceLength(value: number)
Swift declaration
var minimumSequenceLength: Int

The minimum number of samples required to produce a classification. This configuration parameter controls the size of the model. Set it to the largest value that is reasonable for your task. For example if your input is accelerometer data sampled at 100Hz and you want to recognize actions, the minimum action duration may be one second, so the minimum sequence length is `100Hz * 1s = 100`. Defaults to 100.

get · iOS 18.0+

earlyStoppingTolerance

TypeScript
get earlyStoppingTolerance(): number
Swift declaration
var earlyStoppingTolerance: Float

The early-stopping tolerance. The tolerance is used by the `fitted` method to decide when progress is no longer being made, in which case the training process will stop before the specified maximum number of iterations (known as early stopping). Significant progress happens when the validation loss decreases by at least the tolerance. Defaults to 0.01. - Note: Early stopping only happens when using the `fitted` method with validation data.

set · iOS 18.0+

earlyStoppingTolerance

TypeScript
set earlyStoppingTolerance(value: number)
Swift declaration
var earlyStoppingTolerance: Float

The early-stopping tolerance. The tolerance is used by the `fitted` method to decide when progress is no longer being made, in which case the training process will stop before the specified maximum number of iterations (known as early stopping). Significant progress happens when the validation loss decreases by at least the tolerance. Defaults to 0.01. - Note: Early stopping only happens when using the `fitted` method with validation data.

get · iOS 18.0+

earlyStoppingIterationCount

TypeScript
get earlyStoppingIterationCount(): number
Swift declaration
var earlyStoppingIterationCount: Int

The number of iterations to use when evaluating whether to stop early. The `fitted` method will stop if no significant progress is made for this many iterations. Significant progress happens when the validation error decreases by at least `convergenceThreshold`. - Note: Early stopping only happens when using the `fitted` method with validation data.

set · iOS 18.0+

earlyStoppingIterationCount

TypeScript
set earlyStoppingIterationCount(value: number)
Swift declaration
var earlyStoppingIterationCount: Int

The number of iterations to use when evaluating whether to stop early. The `fitted` method will stop if no significant progress is made for this many iterations. Significant progress happens when the validation error decreases by at least `convergenceThreshold`. - Note: Early stopping only happens when using the `fitted` method with validation data.

get · iOS 18.0+

batchSize

TypeScript
get batchSize(): number
Swift declaration
var batchSize: Int

The number of examples in each training batch. - Note: This parameter is only used by the `fitted` method.

set · iOS 18.0+

batchSize

TypeScript
set batchSize(value: number)
Swift declaration
var batchSize: Int

The number of examples in each training batch. - Note: This parameter is only used by the `fitted` method.

init · iOS 18.0+

init

TypeScript
static init(): TimeSeriesClassifierConfiguration
Swift declaration
init()

Creates a configuration.

Skipped declarations

No declarations were skipped in this snapshot.

All CreateMLComponents types →