TolerantEarlyStoppingRule Class

Definition

Namespace:: Microsoft.ML.Trainers.FastTree

Assembly:: Microsoft.ML.FastTree.dll

Package:: Microsoft.ML.FastTree v4.0.1

Package:: Microsoft.ML.FastTree v1.0.0

Package:: Microsoft.ML.FastTree v1.1.0

Package:: Microsoft.ML.FastTree v1.2.0

Package:: Microsoft.ML.FastTree v1.3.1

Package:: Microsoft.ML.FastTree v1.4.0

Package:: Microsoft.ML.FastTree v1.5.5

Package:: Microsoft.ML.FastTree v1.6.0

Package:: Microsoft.ML.FastTree v1.7.0

Package:: Microsoft.ML.FastTree v2.0.1

Package:: Microsoft.ML.FastTree v3.0.1

Package:: Microsoft.ML.FastTree v5.0.0-preview.1.25125.4

Source:: EarlyStoppingCriteria.cs

Source:: EarlyStoppingCriteria.cs

Source:: EarlyStoppingCriteria.cs

Important

Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.

public sealed class TolerantEarlyStoppingRule : Microsoft.ML.Trainers.FastTree.EarlyStoppingRule

type TolerantEarlyStoppingRule = class
    inherit EarlyStoppingRule

Public NotInheritable Class TolerantEarlyStoppingRule
Inherits EarlyStoppingRule

Inheritance: Object

EarlyStoppingRuleBase

EarlyStoppingRule
TolerantEarlyStoppingRule

Constructors

TolerantEarlyStoppingRule(Single)

Create a rule which may terminate the training process if validation score exceeds threshold compared with the best historical validation score.

Properties

Threshold

The upper bound of the indicated metric on validation set.

Methods

CheckScore(Single, Single, Boolean)

See CheckScore(Single, Single, Boolean).

Applies to