org.deeplearning4j.nn.modelimport.keras.layers

Class TFOpLayerImpl

java.lang.Object

org.deeplearning4j.nn.layers.AbstractLayer<TFOpLayer>

org.deeplearning4j.nn.modelimport.keras.layers.TFOpLayerImpl

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model, Trainable

public class TFOpLayerImpl
extends AbstractLayer<TFOpLayer>

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Field Summary

Fields inherited from class org.deeplearning4j.nn.layers.AbstractLayer

cacheMode, conf, dataType, dropoutApplied, epochCount, index, input, inputModificationAllowed, iterationCount, maskArray, maskState, preOutput, trainingListeners

Constructor Summary

Constructors

Constructor and Description
TFOpLayerImpl(Map nodeDef, Map constants, NeuralNetConfiguration conf, DataType dtype)

Method Summary

Modifier and Type	Method and Description
INDArray	activate(boolean training, LayerWorkspaceMgr workspaceMgr)
org.nd4j.common.primitives.Pair<Gradient,INDArray>	backpropGradient(INDArray epsilon, LayerWorkspaceMgr workspaceMgr)
void	clearNoiseWeightParams()
long[]	getOutputShape(long[] inputShape)
boolean	isPretrainLayer()

Methods inherited from class org.deeplearning4j.nn.layers.AbstractLayer

activate, addListeners, allowInputModification, applyConstraints, applyDropOutIfNecessary, applyMask, assertInputSet, backpropDropOutIfPresent, batchSize, calcRegularizationScore, canEqual, clear, close, computeGradientAndScore, conf, equals, feedForwardMaskArray, fit, fit, getCacheMode, getConf, getConfig, getDataType, getEpochCount, getGradientsViewArray, getHelper, getIndex, getInput, getInputMiniBatchSize, getIterationCount, getListeners, getMaskArray, getMaskState, getOptimizer, getParam, getPreOutput, getTrainingListeners, gradient, gradientAndScore, hashCode, init, input, isDropoutApplied, isInputModificationAllowed, layerConf, layerId, numParams, numParams, params, paramTable, paramTable, score, setBackpropGradientsViewArray, setCacheMode, setConf, setDataType, setDropoutApplied, setEpochCount, setIndex, setInput, setInputMiniBatchSize, setInputModificationAllowed, setIterationCount, setListeners, setListeners, setMaskArray, setMaskState, setParam, setParams, setParams, setParamsViewArray, setParamTable, setPreOutput, setTrainingListeners, toString, type, update, update, updaterDivideByMinibatch

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

TFOpLayerImpl

public TFOpLayerImpl(Map nodeDef,
                     Map constants,
                     NeuralNetConfiguration conf,
                     DataType dtype)

Method Detail

backpropGradient

public org.nd4j.common.primitives.Pair<Gradient,INDArray> backpropGradient(INDArray epsilon,
                                                                           LayerWorkspaceMgr workspaceMgr)

getOutputShape

public long[] getOutputShape(long[] inputShape)

activate

public INDArray activate(boolean training,
                         LayerWorkspaceMgr workspaceMgr)

isPretrainLayer

public boolean isPretrainLayer()

clearNoiseWeightParams

public void clearNoiseWeightParams()