Class ReduceLROnPlateau

Reduce learning rate when a metric has stopped improving. Models often benefit from reducing the learning rate by a factor of 2-10 once learning stagnates. This callback monitors a quantity and if no improvement is seen for a 'patience' number of epochs, the learning rate is reduced.

Inheritance

System.Object

Keras

Base

Callback

ReduceLROnPlateau

Implements

System.IDisposable

Inherited Members

Base.Parameters

Base.None

Base.Init()

Base.ToPython()

Base.InvokeStaticMethod(Object, String, Dictionary<String, Object>)

Base.InvokeMethod(String, Dictionary<String, Object>)

Base.Item[String]

Keras.Instance

Keras.keras

Keras.keras2onnx

Keras.tfjs

Keras.Dispose()

Keras.ToTuple(Array)

Keras.ToList(Array)

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: Keras.Callbacks

Assembly: Keras.dll

Syntax

public class ReduceLROnPlateau : Callback, IDisposable

Constructors

ReduceLROnPlateau(String, Single, Int32, Int32, String, Single, Int32, Single)

Initializes a new instance of the LearningRateScheduler class.

Declaration

public ReduceLROnPlateau(string monitor = "val_loss", float factor = 0.1F, int patience = 10, int verbose = 0, string mode = "auto", float min_delta = 0.0001F, int cooldown = 0, float min_lr = 0F)

Parameters

Type	Name	Description
System.String	monitor	quantity to be monitored.
System.Single	factor	factor by which the learning rate will be reduced. new_lr = lr * factor
System.Int32	patience	number of epochs with no improvement after which learning rate will be reduced.
System.Int32	verbose	int. 0: quiet, 1: update messages.
System.String	mode	one of {auto, min, max}. In min mode, lr will be reduced when the quantity monitored has stopped decreasing; in max mode it will be reduced when the quantity monitored has stopped increasing; in auto mode, the direction is automatically inferred from the name of the monitored quantity.
System.Single	min_delta	threshold for measuring the new optimum, to only focus on significant changes.
System.Int32	cooldown	number of epochs to wait before resuming normal operation after lr has been reduced.
System.Single	min_lr	lower bound on the learning rate.

Implements

System.IDisposable