Package mklab.JGNN.nn.pooling

Class Mean

java.lang.Object

mklab.JGNN.nn.NNOperation

mklab.JGNN.nn.pooling.Mean

public class Mean
extends NNOperation

Implements a NNOperation that performs row-wise or column-wise mean reduction on vector tensors or matrices.

Author:

Emmanouil Krasanakis

Nested Class Summary

Nested classes/interfaces inherited from class mklab.JGNN.nn.NNOperation

NNOperation.ThreadData

Field Summary

Fields inherited from class mklab.JGNN.nn.NNOperation

debugging

Constructor Summary

Constructors

Constructor	Description
Mean()
Mean(boolean colMode)

Method Summary

Modifier and Type	Method	Description
Tensor	forward(List<Tensor> inputs)
protected Tensor	partial(int inputId, List<Tensor> inputs, Tensor output, Tensor error)

Methods inherited from class mklab.JGNN.nn.NNOperation

addInput, autosize, clearPrediction, data, describe, getDescription, getInputs, getLastTapeError, getNonLinearity, getOutputs, getPrediction, getSimpleDescription, isCachable, isConstant, isInputNeededForDerivative, isOutputNeededForDerivative, run, run, runPrediction, runPredictionAndAutosize, setDescription, trainParameters, view

Methods inherited from class java.lang.Object

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

Constructor Details

Mean

public Mean()

Mean

public Mean(boolean colMode)

Method Details

forward

public Tensor forward(List<Tensor> inputs)

Specified by:

forward in class NNOperation

partial

protected Tensor partial(int inputId,
 List<Tensor> inputs,
 Tensor output,
 Tensor error)

Specified by:

partial in class NNOperation