Uses of Class
deepnetts.tensor.TensorBase

Packages that use TensorBase

Package	Description
deepnetts.accl.spi
deepnetts.data	Data structures to store example data used for building machine learning models.
deepnetts.data.norm	Data normalization methods, used to scale data to specific range, in order to make them suitable for use by a neural network.
deepnetts.net	Neural network architectures with their corresponding builders.
deepnetts.net.layers	Neural network layers, which are main building blocks of a neural network.
deepnetts.net.loss	Commonly used loss functions, which are used to calculate error during the training as a difference between predicted and target output.
deepnetts.net.train.opt	Optimization methods used by training algorithm.
deepnetts.tensor
deepnetts.util	Various utility classes including Tensor, image operations, multithreading, exceptions etc.

Uses of TensorBase in deepnetts.accl.spi

Methods in deepnetts.accl.spi with parameters of type TensorBase

Modifier and Type	Method	Description
AcceleratorTensorBridge	AcceleratorProvider.createAcceleratorTensorBridge(TensorBase tensor)

Uses of TensorBase in deepnetts.data

Methods in deepnetts.data that return TensorBase

Modifier and Type	Method	Description
TensorBase	DataSetItem.getInput()
TensorBase	MLDataItem.getInput()	Returns an input for machine learning model of this item.
TensorBase	ImageSet.getMean()
TensorBase	DataSetItem.getTargetOutput()
TensorBase	ExampleImage.getTargetOutput()
TensorBase	MLDataItem.getTargetOutput()	Returns target output for machine learning model of this item.
TensorBase	ImageSet.zeroMean()	Applies zero mean normalization to entire dataset, and returns mean tensor.
TensorBase	ImageSet.zeroMeanAndNormalize()
TensorBase	ImageSet.zeroMeanPerChannel()

Methods in deepnetts.data with parameters of type TensorBase

Modifier and Type	Method	Description
final void	ExampleImage.setTargetOutput(TensorBase targetOutput)

Constructors in deepnetts.data with parameters of type TensorBase

Modifier	Constructor	Description
	DataSetItem(TensorBase input, TensorBase targetOutput)

Uses of TensorBase in deepnetts.data.norm

Methods in deepnetts.data.norm that return TensorBase

Modifier and Type	Method	Description
TensorBase	MaxScaler.getMaxInputs()
TensorBase	MaxScaler.getMaxOutputs()

Methods in deepnetts.data.norm with parameters of type TensorBase

Modifier and Type	Method	Description
void	MaxScaler.deNormalizeInputs(TensorBase inputs)
void	MaxScaler.deNormalizeOutputs(TensorBase outputs)	De-normalize given output vector in-place.
void	MaxScaler.normalizeInput(TensorBase input)
abstract void	AbstractScaler.scaleInput(TensorBase input)	Normalize input of deployed model
void	DecimalScaler.scaleInput(TensorBase input)
void	MaxScaler.scaleInput(TensorBase input)
void	MinMaxScaler.scaleInput(TensorBase input)
void	RangeScaler.scaleInput(TensorBase input)
void	Standardizer.scaleInput(TensorBase input)
void	MaxScaler.setMaxInputs(TensorBase maxInputs)
void	MaxScaler.setMaxOutputs(TensorBase maxOutputs)

Uses of TensorBase in deepnetts.net

Methods in deepnetts.net that return TensorBase

Modifier and Type	Method	Description
TensorBase	NeuralNetwork.getOutputAsTensor()
TensorBase	NeuralNetwork.predict(TensorBase input)	Returns the prediction of this neural network for the given input.

Methods in deepnetts.net that return types with arguments of type TensorBase

Modifier and Type	Method	Description
List<TensorBase>	ConvolutionalNetwork.getDeltaWeights()	Returns delta weights for all layers.
List<TensorBase>	ConvolutionalNetwork.getLayersGradients()
List<TensorBase>	ConvolutionalNetwork.getLayersOutputs()	Returns outputs of all layers.
List<TensorBase>	ConvolutionalNetwork.getWeights()	Returns weights from all layers in this network as a list of tensors.

Methods in deepnetts.net with parameters of type TensorBase

Modifier and Type	Method	Description
TensorBase	NeuralNetwork.predict(TensorBase input)	Returns the prediction of this neural network for the given input.
void	ConvolutionalNetwork.setInput(TensorBase input)
void	NeuralNetwork.setInput(TensorBase inputs)	Sets network input and calculates entire network (triggers forward pass).
void	NeuralNetwork.setOutputError(TensorBase outputErrors)	Sets the network's output errors, which are a difference between actual(predicted) and target output.

Uses of TensorBase in deepnetts.net.layers

Classes in deepnetts.net.layers with type parameters of type TensorBase

Modifier and Type	Class	Description
class	AbstractLayer<I extends TensorBase, O extends TensorBase, W extends TensorBase>	Base class for different types of layers.
class	AbstractLayer<I extends TensorBase, O extends TensorBase, W extends TensorBase>	Base class for different types of layers.
class	AbstractLayer<I extends TensorBase, O extends TensorBase, W extends TensorBase>	Base class for different types of layers.

Subclasses with type arguments of type TensorBase in deepnetts.net.layers

Modifier and Type	Class	Description
class	CBOWEmbeddingLayer
class	CBOWEmbeddingLayer
final class	ConvolutionalLayer	Convolutional layer performs image convolution operation on outputs of a previous layer using filters.
final class	ConvolutionalLayer	Convolutional layer performs image convolution operation on outputs of a previous layer using filters.
class	EmbeddingLayer
class	EmbeddingLayer
class	FlatEmbeddingLayer
class	FlatEmbeddingLayer
class	FlattenLayer	Transforms outputs from previous 3D layer into a flatten 1D tensor in forward pass, Backward pass propagates weighted errors/deltas from the next fully connected layer.
class	FlattenLayer	Transforms outputs from previous 3D layer into a flatten 1D tensor in forward pass, Backward pass propagates weighted errors/deltas from the next fully connected layer.
class	FlattenLayer	Transforms outputs from previous 3D layer into a flatten 1D tensor in forward pass, Backward pass propagates weighted errors/deltas from the next fully connected layer.
class	FullyConnectedLayer	Fully connected layer is used as a hidden layer in a neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer.
class	FullyConnectedLayer	Fully connected layer is used as a hidden layer in a neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer.
class	LayerNorm
class	LayerNorm
class	LayerNorm
final class	MaxPoolingLayer	This layer performs max pooling operation in convolutional neural network, which scales down output from previous layer by taking max outputs from small predefined filter areas.
final class	MaxPoolingLayer	This layer performs max pooling operation in convolutional neural network, which scales down output from previous layer by taking max outputs from small predefined filter areas.
final class	MaxPoolingLayer	This layer performs max pooling operation in convolutional neural network, which scales down output from previous layer by taking max outputs from small predefined filter areas.
class	OutputLayer	Output layer of a neural network.
class	OutputLayer	Output layer of a neural network.
class	SkipGramEmbeddingLayer
class	SkipGramEmbeddingLayer

Fields in deepnetts.net.layers declared as TensorBase

Modifier and Type	Field	Description
protected O	AbstractLayer.deltas	Deltas used for learning.
protected W	AbstractLayer.deltaWeights	Weight changes for current and previous iteration.
protected W	AbstractLayer.gradients	Gradients of a loss function calculates during a backward pass.
protected I	AbstractLayer.inputs	Inputs to this layer.
protected TensorBase	OutputLayer.outputErrors
protected O	AbstractLayer.outputs	Layer outputs.
protected W	AbstractLayer.prevDeltaWeights	Weight changes for current and previous iteration.
protected W	AbstractLayer.weights	Input weight matrix / connectivity matrix for previous layer.

Methods in deepnetts.net.layers that return TensorBase

Modifier and Type	Method	Description
TensorBase	ConvolutionalLayer.getFilterDeltaWeights()
TensorBase	ConvolutionalLayer.getFilters()
final TensorBase	OutputLayer.getOutputErrors()

Methods in deepnetts.net.layers with parameters of type TensorBase

Modifier and Type	Method	Description
void	InputLayer.setInput(TensorBase in)	Sets network input
final void	OutputLayer.setOutputErrors(TensorBase outputErrors)

Uses of TensorBase in deepnetts.net.loss

Methods in deepnetts.net.loss that return TensorBase

Modifier and Type	Method	Description
TensorBase	BinaryCrossEntropyLoss.addPatternError(TensorBase predictedOutput, TensorBase targetOutput)	Calculates error for given actual and target patterns and adds that error to total error.
TensorBase	CrossEntropyLoss.addPatternError(TensorBase predictedOut, TensorBase targetOut)	Calculates and returns outpurt error vector for specified predicted and target outputs.
TensorBase	LossFunction.addPatternError(TensorBase predictedOutput, TensorBase targetOutput)	Calculates pattern error for singe pattern for the specified predicted and target outputs, adds the error to total error, and returns the pattern error.
TensorBase	MeanSquaredErrorLoss.addPatternError(TensorBase predictedOut, TensorBase targetOut)	Adds output error vector for the given predicted and target output vectors to total error sum and returns and error vector.

Methods in deepnetts.net.loss with parameters of type TensorBase

Modifier and Type	Method	Description
TensorBase	BinaryCrossEntropyLoss.addPatternError(TensorBase predictedOutput, TensorBase targetOutput)	Calculates error for given actual and target patterns and adds that error to total error.
TensorBase	CrossEntropyLoss.addPatternError(TensorBase predictedOut, TensorBase targetOut)	Calculates and returns outpurt error vector for specified predicted and target outputs.
TensorBase	LossFunction.addPatternError(TensorBase predictedOutput, TensorBase targetOutput)	Calculates pattern error for singe pattern for the specified predicted and target outputs, adds the error to total error, and returns the pattern error.
TensorBase	MeanSquaredErrorLoss.addPatternError(TensorBase predictedOut, TensorBase targetOut)	Adds output error vector for the given predicted and target output vectors to total error sum and returns and error vector.

Uses of TensorBase in deepnetts.net.train.opt

Fields in deepnetts.net.train.opt declared as TensorBase

Modifier and Type	Field	Description
protected TensorBase	AbstractOptimizer.deltaBiases
protected TensorBase	AbstractOptimizer.deltas
protected TensorBase	AbstractOptimizer.deltaWeights
protected TensorBase	AbstractOptimizer.gradients
protected TensorBase	AbstractOptimizer.inputs

Methods in deepnetts.net.train.opt that return TensorBase

Modifier and Type	Method	Description
TensorBase	AdaDeltaOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	AdaGradOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	AdamOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	MomentumOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	Optimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	RmsPropOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	SgdOptimizer.calculateDeltaWeight(TensorBase grad)

Methods in deepnetts.net.train.opt with parameters of type TensorBase

Modifier and Type	Method	Description
TensorBase	AdaDeltaOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	AdaGradOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	AdamOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	MomentumOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	Optimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	RmsPropOptimizer.calculateDeltaWeight(TensorBase grad)
TensorBase	SgdOptimizer.calculateDeltaWeight(TensorBase grad)

Uses of TensorBase in deepnetts.tensor

Subclasses of TensorBase in deepnetts.tensor

Modifier and Type	Class	Description
class	Tensor1D	One dimensional tensor - a vector or an array.
final class	Tensor2D	A 2D tensor / matrix with specified number of rows and columns..
class	Tensor3D	A 3D tensor/matrix, with rows, columns and depth.
class	Tensor4D

Methods in deepnetts.tensor that return TensorBase

Modifier and Type	Method	Description
static TensorBase	Tensors.absMax(Tensor t, Tensor max)	Returns tensors with max value for each component of input tensors.
static TensorBase	Tensors.absMin(TensorBase t, TensorBase min)
final TensorBase	TensorBase.add(float val)
final TensorBase	TensorBase.add(TensorBase t)	Adds specified tensor t to this tensor.
final TensorBase	TensorBase.addInto(TensorBase t, TensorBase result)
TensorBase	TensorBase.apply(ActivationFunction af)
TensorBase	Tensor1D.copy()
TensorBase	Tensor2D.copy()
TensorBase	Tensor3D.copy()
TensorBase	Tensor4D.copy()
TensorBase	TensorBase.copy()
TensorBase	TensorBase.multiply(float m)	Multiplies all the values in tensor with a specified input parameter.
TensorBase	TensorBase.sqr()
TensorBase	TensorBase.sqrt()
final TensorBase	TensorBase.sub(TensorBase t, TensorBase result)

Methods in deepnetts.tensor with parameters of type TensorBase

Modifier and Type	Method	Description
static TensorBase	Tensors.absMin(TensorBase t, TensorBase min)
final TensorBase	TensorBase.add(TensorBase t)	Adds specified tensor t to this tensor.
final TensorBase	TensorBase.addInto(TensorBase t, TensorBase result)
final void	TensorBase.copyFrom(TensorBase src)	Copies values from specified tensor
final void	TensorBase.div(TensorBase t)	Element-wise divison with specified tensor.
boolean	TensorBase.equals(TensorBase t2, float delta)
void	TensorBase.multiplyElementWise(TensorBase tensor2)
final void	TensorBase.sub(TensorBase t)	Subtracts specified tensor t from this tensor.
final TensorBase	TensorBase.sub(TensorBase t, TensorBase result)
static final void	TensorBase.subInplace(TensorBase t1, TensorBase t2)	Subtracts tensor t2 from t1.
static String	TensorBase.valuesAsString(TensorBase[] tensors)

Constructors in deepnetts.tensor with parameters of type TensorBase

Modifier	Constructor	Description
protected	TensorBase(TensorBase t)	Public deep copy / clone constructor.

Uses of TensorBase in deepnetts.util

Methods in deepnetts.util that return TensorBase

Modifier and Type	Method	Description
TensorBase	ImagePreprocessing.getMean()

Methods in deepnetts.util with parameters of type TensorBase

Modifier and Type	Method	Description
void	ImagePreprocessing.setMean(TensorBase mean)