Class TimeseriesGenerator

Utility class for generating batches of temporal data. This class takes in a sequence of data-points gathered at equal intervals, along with time series parameters such as stride, length of history, etc., to produce batches for training/validation.

Inheritance

System.Object

Keras

Base

Sequence

TimeseriesGenerator

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.PreProcessing.sequence

Assembly: Keras.dll

Syntax

public class TimeseriesGenerator : Sequence, IDisposable

Constructors

TimeseriesGenerator(NDarray, NDarray, Int32, Int32, Int32, Int32, Nullable<Int32>, Boolean, Boolean, Int32)

Initializes a new instance of the TimeseriesGenerator class.

Declaration

public TimeseriesGenerator(NDarray data, NDarray targets, int length, int sampling_rate = 1, int stride = 1, int start_index = 0, int? end_index = default(int? ), bool shuffle = false, bool reverse = false, int batch_size = 128)

Parameters

Type	Name	Description
Numpy.NDarray	data	The data.
Numpy.NDarray	targets	The targets.
System.Int32	length	The length.
System.Int32	sampling_rate	The sampling rate.
System.Int32	stride	The stride.
System.Int32	start_index	The start index.
System.Nullable<System.Int32>	end_index	The end index.
System.Boolean	shuffle	if set to true [shuffle].
System.Boolean	reverse	if set to true [reverse].
System.Int32	batch_size	Size of the batch.

Implements

System.IDisposable