Class SoftmaxOutputLayer

java.lang.Object

deepnetts.net.layers.AbstractLayer<TensorBase, TensorBase, Tensor2D>

deepnetts.net.layers.OutputLayer

deepnetts.net.layers.SoftmaxOutputLayer

All Implemented Interfaces:

Backward, Forward, Layer<TensorBase>, Serializable

public class SoftmaxOutputLayer
extends OutputLayer

Output layer with softmax activation function.

Author:

Zoran Sevarac

See Also:

• Serialized Form

Field Summary

Fields inherited from class OutputLayer

backwardTasks, forwardTasks, labels, lossType, multithreaded, outputErrors

Fields inherited from class AbstractLayer

activation, activationType, backwardImpl, batchMode, batchSize, biases, cudaHandles, deltaBiases, deltas, deltaWeights, depth, forwardImpl, gradients, height, inputs, learningRate, mode, momentum, networkType, nextLayer, numThreads, optimizer, optimizerType, outputs, prevDeltaBiases, prevDeltaWeights, prevLayer, randomWeightsType, regL1, regL2, threadPool, trainable, weights, width

Constructor Summary

Constructors

Constructor	Description
SoftmaxOutputLayer(int size)

Method Summary

Modifier and Type	Method	Description
void	applySoftmax(Tensor1D outputs1D, float maxWs)	/ prva implementacija single threaded ubaci da izvrti batch u for petlji, onda paralelizuj batch
void	applySoftmaxBatch(Tensor2D inputs2D, Tensor2D outputs2D)
void	backward()	Performs backward pass for this layer.
void	forward()	Forward pass for the output layer, calculates layer outputs using softmax function.
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()

Methods inherited from class OutputLayer

applyWeightChanges, getLossType, getOutputErrors, getSingleOutInput, setLossType, setOutputErrors, toString

Methods inherited from class AbstractLayer

getActivation, getActivationType, getBackwardAcc, getBatchSize, getBiases, getDeltaBiases, getDeltas, getDeltaWeights, getDepth, getForwardAcc, getGradients, getHeight, getL1Regularization, getL1WeightSum, getL2Regularization, getL2WeightSum, getLearningRate, getMode, getMomentum, getNetworkType, getNextLayer, getNumThreads, getOptimizer, getOptimizerType, getOutputs, getPrevDeltaBiases, getPrevDeltaWeights, getPrevlayer, getWeights, getWidth, isBatchMode, isTrainable, setActivationType, setBatchMode, setBatchSize, setBiases, setCudaHandles, setDeltas, setL1Regularization, setL2Regularization, setLearningRate, setMode, setMomentum, setNetworkType, setNextlayer, setOptimizerType, setOutputs, setPrevDeltaWeights, setPrevLayer, setThreadPool, setTrainable, setWeights, setWeights

Methods inherited from class Object

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

Constructor Details

SoftmaxOutputLayer

public SoftmaxOutputLayer(int size)

Method Details

init

public void init()

Description copied from class: AbstractLayer

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

Overrides:

init in class OutputLayer

initTransientFields

public void initTransientFields()

Overrides:

initTransientFields in class OutputLayer

forward

public void forward()

Forward pass for the output layer, calculates layer outputs using softmax function.

Specified by:

forward in interface Forward

Specified by:

forward in interface Layer<TensorBase>

Overrides:

forward in class OutputLayer

backward

public void backward()

Performs backward pass for this layer.

Specified by:

backward in interface Backward

Specified by:

backward in interface Layer<TensorBase>

Overrides:

backward in class OutputLayer

applySoftmax

public void applySoftmax(Tensor1D outputs1D,
 float maxWs)

/ prva implementacija single threaded ubaci da izvrti batch u for petlji, onda paralelizuj batch

applySoftmaxBatch

public void applySoftmaxBatch(Tensor2D inputs2D,
 Tensor2D outputs2D)