Class PReLU
- java.lang.Object
-
- org.deeplearning4j.nn.layers.AbstractLayer<LayerConfT>
-
- org.deeplearning4j.nn.layers.BaseLayer<PReLULayer>
-
- org.deeplearning4j.nn.layers.feedforward.PReLU
-
- All Implemented Interfaces:
Serializable
,Cloneable
,Layer
,Model
,Trainable
public class PReLU extends BaseLayer<PReLULayer>
- 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.BaseLayer
gradient, gradientsFlattened, gradientViews, optimizer, params, paramsFlattened, score, solver, weightNoiseParams
-
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 Description PReLU(NeuralNetConfiguration conf, DataType dataType)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description INDArray
activate(boolean training, LayerWorkspaceMgr mgr)
Perform forward pass and return the activations array with the last set inputPair<Gradient,INDArray>
backpropGradient(INDArray epsilon, LayerWorkspaceMgr workspaceMgr)
Calculate the gradient relative to the error in the next layerboolean
isPretrainLayer()
Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)Layer.Type
type()
Returns the layer type-
Methods inherited from class org.deeplearning4j.nn.layers.BaseLayer
calcRegularizationScore, clear, clearNoiseWeightParams, clone, computeGradientAndScore, fit, fit, getGradientsViewArray, getOptimizer, getParam, getParamWithNoise, gradient, hasBias, hasLayerNorm, layerConf, numParams, params, paramTable, paramTable, preOutput, preOutputWithPreNorm, score, setBackpropGradientsViewArray, setParam, setParams, setParams, setParamsViewArray, setParamTable, setScoreWithZ, toString, update, update
-
Methods inherited from class org.deeplearning4j.nn.layers.AbstractLayer
activate, addListeners, allowInputModification, applyConstraints, applyDropOutIfNecessary, applyMask, assertInputSet, backpropDropOutIfPresent, batchSize, close, conf, feedForwardMaskArray, getConfig, getEpochCount, getHelper, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, gradientAndScore, init, input, layerId, numParams, setCacheMode, setConf, setEpochCount, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, updaterDivideByMinibatch
-
Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
-
Methods inherited from interface org.deeplearning4j.nn.api.Layer
getIterationCount, setIterationCount
-
-
-
-
Constructor Detail
-
PReLU
public PReLU(NeuralNetConfiguration conf, DataType dataType)
-
-
Method Detail
-
type
public Layer.Type type()
Description copied from interface:Layer
Returns the layer type- Specified by:
type
in interfaceLayer
- Overrides:
type
in classAbstractLayer<PReLULayer>
- Returns:
-
activate
public INDArray activate(boolean training, LayerWorkspaceMgr mgr)
Description copied from interface:Layer
Perform forward pass and return the activations array with the last set input- Specified by:
activate
in interfaceLayer
- Overrides:
activate
in classBaseLayer<PReLULayer>
- Parameters:
training
- training or test modemgr
- Workspace manager- Returns:
- the activation (layer output) of the last specified input. Note that the returned array should be placed
in the
ArrayType.ACTIVATIONS
workspace via the workspace manager
-
backpropGradient
public Pair<Gradient,INDArray> backpropGradient(INDArray epsilon, LayerWorkspaceMgr workspaceMgr)
Description copied from interface:Layer
Calculate the gradient relative to the error in the next layer- Specified by:
backpropGradient
in interfaceLayer
- Overrides:
backpropGradient
in classBaseLayer<PReLULayer>
- Parameters:
epsilon
- w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.workspaceMgr
- Workspace manager- Returns:
- Pair
where Gradient is gradient for this layer, INDArray is epsilon (activation gradient) needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == dL/dIn = (w^(L)*(delta^(L))^T)^T. Note that the returned array should be placed in the ArrayType.ACTIVATION_GRAD
workspace via the workspace manager
-
isPretrainLayer
public boolean isPretrainLayer()
Description copied from interface:Layer
Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)- Returns:
- true if the layer can be pretrained (using fit(INDArray), false otherwise
-
-