Package deepnetts.data.norm

Class RangeScaler

java.lang.Object

deepnetts.data.norm.AbstractScaler

deepnetts.data.norm.RangeScaler

All Implemented Interfaces:

Serializable, javax.visrec.ml.data.preprocessing.Scaler<javax.visrec.ml.data.DataSet<MLDataItem>>

public class RangeScaler
extends AbstractScaler

Normalize data set to specified range. Using formula X = (X-MIN) / (MAX-MIN) Effectively scales all inputs and outputs to specified [MIN,MAX] range Normalizes inputs and outputs.

Author:

Zoran Sevarac

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
RangeScaler(float min, float max)	Creates a new instance of range normalizer initialized to given min and max values.

Method Summary

Modifier and Type	Method	Description
void	apply(javax.visrec.ml.data.DataSet<MLDataItem> dataSet)	Performs normalization on the given inputs.
void	scaleInput(TensorBase input)	Normalize input of deployed model

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

RangeScaler

public RangeScaler(float min,
 float max)

Creates a new instance of range normalizer initialized to given min and max values.

Parameters:

min -

max -

Method Details

apply

public void apply(javax.visrec.ml.data.DataSet<MLDataItem> dataSet)

Performs normalization on the given inputs. x = (x-min) / (max-min)

Parameters:

dataSet - data set to normalize

scaleInput

public void scaleInput(TensorBase input)

Description copied from class: AbstractScaler

Normalize input of deployed model

Specified by:

scaleInput in class AbstractScaler

Parameters:

input -