Package deepnetts.net.layers

Class AbstractLayer<I extends TensorBase,O extends TensorBase,W extends TensorBase>

java.lang.Object

deepnetts.net.layers.AbstractLayer<I,O,W>

Type Parameters:

O - output tensor class

W - weights tensor class

All Implemented Interfaces:

Layer<O>, Serializable

Direct Known Subclasses:

ConvolutionalLayer, FlattenLayer, FullyConnectedLayer, InputLayer, MaxPoolingLayer, OutputLayer

public abstract class AbstractLayer<I extends TensorBase,O extends TensorBase,W extends TensorBase>
extends Object
implements Layer<O>, Serializable

Base class for different types of layers. Provides common functionality for all type of layers: layer dimensions, inputs, outputs, connection to previous and/or next layer, activation function and abstract methods for initialization, forward and backward pass.

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
AbstractLayer(ActivationType activationType)

Method Summary

Modifier and Type	Method	Description
abstract void	applyWeightChanges()	Applies weight changes to current weights Must be diferent for convolutional does nothing for MaxPooling Same for FullyConnected and OutputLayer
abstract void	backward()	This method should implement backward pass in subclasses
abstract void	forward()	This method should implement forward pass in subclasses
ActivationFunction	getActivation()
ActivationType	getActivationType()
float	getBatchSize()
TensorBase	getBiases()
Tensor1D	getDeltaBiases()
final O	getDeltas()	Returns layer deltas/errors (as a tensor).
W	getDeltaWeights()
int	getDepth()
ForwardAccelerator	getForwardAccelerator()
final TensorBase	getGradients()
int	getHeight()
float	getL1Regularization()
float	getL1WeightSum()
float	getL2Regularization()
float	getL2WeightSum()
float	getLearningRate()
Mode	getMode()
float	getMomentum()
AbstractLayer	getNextLayer()
Optimizer	getOptimizer()
OptimizerType	getOptimizerType()
final O	getOutputs()	Returns layer outputs (as a tensor).
Tensor1D	getPrevDeltaBiases()
W	getPrevDeltaWeights()
AbstractLayer	getPrevlayer()
W	getWeights()
int	getWidth()
abstract void	init()	This method should implement layer initialization in subclasses, when a layer is added to the network (create weights, outputs, deltas, randomization etc.).
void	initTransientFields()
boolean	isBatchMode()
boolean	isTrainable()
void	setBatchMode(boolean batchMode)
void	setBatchSize(int batchSize)
void	setBiases(Tensor1D biases)
void	setCudaHandles(CudaHandles cudaHandles)
final void	setDeltas(O deltas)
void	setL1Regularization(float regL1)
void	setL2Regularization(float regL2)
void	setLearningRate(float learningRate)
void	setMode(Mode mode)
void	setMomentum(float momentum)
void	setNextlayer(AbstractLayer nextlayer)
void	setOptimizerType(OptimizerType optType)
final void	setOutputs(O outputs)
void	setPrevDeltaWeights(W prevDeltaWeights)
void	setPrevLayer(AbstractLayer prevLayer)
void	setThreadPool(DeepNettsThreadPool threadPool)
void	setTrainable(boolean trainable)	Set trainable to false to freeze learned weights.
void	setWeights(String weightStr)
void	setWeights(W weights)

Methods inherited from class java.lang.Object

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

Constructor Details

AbstractLayer

public AbstractLayer(ActivationType activationType)

Method Details

init

public abstract void init()

This method should implement layer initialization in subclasses, when a layer is added to the network (create weights, outputs, deltas, randomization etc.).

forward

public abstract void forward()

This method should implement forward pass in subclasses

Specified by:

forward in interface Layer<I extends TensorBase>

backward

public abstract void backward()

This method should implement backward pass in subclasses

Specified by:

backward in interface Layer<I extends TensorBase>

applyWeightChanges

public abstract void applyWeightChanges()

Applies weight changes to current weights Must be diferent for convolutional does nothing for MaxPooling Same for FullyConnected and OutputLayer

getWidth

public int getWidth()

getHeight

public int getHeight()

getDepth

public int getDepth()

getPrevlayer

public AbstractLayer getPrevlayer()

setPrevLayer

public void setPrevLayer(AbstractLayer prevLayer)

setNextlayer

public void setNextlayer(AbstractLayer nextlayer)

getNextLayer

public AbstractLayer getNextLayer()

getWeights

public W getWeights()

getBiases

public TensorBase getBiases()

setBiases

public void setBiases(Tensor1D biases)

getOutputs

public final O getOutputs()

Description copied from interface: Layer

Returns layer outputs (as a tensor).

Specified by:

getOutputs in interface Layer<I extends TensorBase>

Returns:

layer output as a tensor

getDeltas

public final O getDeltas()

Description copied from interface: Layer

Returns layer deltas/errors (as a tensor). Deltas are accumulated errors propagated from the next layer.

Specified by:

getDeltas in interface Layer<I extends TensorBase>

Returns:

layer deltas tensor

getGradients

public final TensorBase getGradients()

getDeltaWeights

public W getDeltaWeights()

getPrevDeltaWeights

public W getPrevDeltaWeights()

setPrevDeltaWeights

public void setPrevDeltaWeights(W prevDeltaWeights)

getPrevDeltaBiases

public Tensor1D getPrevDeltaBiases()

getDeltaBiases

public Tensor1D getDeltaBiases()

setOutputs

public final void setOutputs(O outputs)

setWeights

public void setWeights(W weights)

setWeights

public void setWeights(String weightStr)

setDeltas

public final void setDeltas(O deltas)

getActivation

public ActivationFunction getActivation()

getOptimizer

public Optimizer getOptimizer()

getLearningRate

public float getLearningRate()

setLearningRate

public void setLearningRate(float learningRate)

isBatchMode

public boolean isBatchMode()

setBatchMode

public void setBatchMode(boolean batchMode)

getBatchSize

public float getBatchSize()

setBatchSize

public void setBatchSize(int batchSize)

setMomentum

public void setMomentum(float momentum)

getMomentum

public float getMomentum()

getOptimizerType

public OptimizerType getOptimizerType()

setOptimizerType

public void setOptimizerType(OptimizerType optType)

getActivationType

public ActivationType getActivationType()

getL1WeightSum

public float getL1WeightSum()

getL2WeightSum

public float getL2WeightSum()

getL2Regularization

public float getL2Regularization()

setL2Regularization

public void setL2Regularization(float regL2)

getL1Regularization

public float getL1Regularization()

setL1Regularization

public void setL1Regularization(float regL1)

isTrainable

public boolean isTrainable()

setTrainable

public void setTrainable(boolean trainable)

Set trainable to false to freeze learned weights.

Parameters:

trainable -

initTransientFields

public void initTransientFields()

setCudaHandles

public void setCudaHandles(CudaHandles cudaHandles)

getMode

public Mode getMode()

setMode

public void setMode(Mode mode)

getForwardAccelerator

public ForwardAccelerator getForwardAccelerator()

setThreadPool

public void setThreadPool(DeepNettsThreadPool threadPool)