Package deepnetts.tensor

Class TensorBase

java.lang.Object

deepnetts.tensor.TensorBase

All Implemented Interfaces:

Tensor, Serializable

Direct Known Subclasses:

Tensor1D, Tensor2D, Tensor3D, Tensor4D

public class TensorBase
extends Object
implements Tensor, Serializable

This class represents a wrapper for multidimensional array. It a basic data structure for storing inputs, outputs and internal parameters(weights) of the deep learning model. It supports up to 4 dimensions - it can be 1D, 2D, 3D or 4D.

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
TensorBase(Shape shape, float... values)
TensorBase(TensorBase t)	Public deep copy / clone constructor.

Method Summary

Modifier and Type	Method	Description
final void	add(float val)
final TensorBase	add(TensorBase t)	Adds specified tensor t to this tensor.
final TensorBase	addInto(TensorBase t, TensorBase result)
TensorBase	apply(ActivationFunction af)
void	apply(Function<Float,Float> f)	Applies specified function to all elements in tensor in-place.
Object	clone()
TensorBase	copy()
final void	copyFrom(float[] src)
final void	copyFrom(TensorBase src)
void	copyFromGPU()
void	copyToGPU()
TensorAcceleratorBridge	createAcceleratorBridge()
final void	div(float value)	Divide all values in this tensor with specified value.
final void	div(float[] divisors)
final void	div(TensorBase t)	Element-wise divison with specified tensor.
boolean	equals(TensorBase t2, float delta)
boolean	equals(Object obj)
final void	fill(float value)	Fills the entire tensor with specified value.
TensorAcceleratorBridge	getAcceleratorBridge()
TensorAcceleratorBridge	getOrCreateAccBridge()
final float[]	getValues()	Returns values stored in this tensor.
int	hashCode()
float	mean()
TensorBase	multiply(float m)	Multiplies all the values in tensor with a specified input parameter.
void	multiply(float mul, int idx)
void	multiplyElementWise(TensorBase tensor2)
final int	numDimensions()	Rank corresponds to number of dimensions in tensor.
final int	numElements()	Total number of values in tensor.
void	randomize()	Randomize all values in tensor
void	replace(float toReplace, float replaceWith)
final void	setValues(float... values)
void	setValuesFromString(String values)	Sets tensor values from CSV string.
void	setValuesFromStringTransposed(String values)
Shape	shape()	Returns the shape of this tensor.
TensorBase	sqr()
void	sqrt()
float	std(float mean)
final void	sub(float val)
final void	sub(TensorBase t)	Subtracts specified tensor t from this tensor.
static final void	subInplace(TensorBase t1, TensorBase t2)	Subtracts tensor t2 from t1.
final TensorBase	subInto(TensorBase t, TensorBase result)
float	sum()
float	sumAbs()	Returns sum of abs values of this tensor - L1 norm
float	sumSqr()	Returns sum of squared values of this tensor - L2 norm
String	toString()
static String	valuesAsString(TensorBase[] tensors)

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Constructor Details

TensorBase

public TensorBase(Shape shape,
 float... values)

TensorBase

public TensorBase(TensorBase t)

Public deep copy / clone constructor.

Parameters:

t -

Method Details

clone

public Object clone()

getValues

public final float[] getValues()

Description copied from interface: Tensor

Returns values stored in this tensor.

Specified by:

getValues in interface Tensor

Returns:

setValues

public final void setValues(float... values)

copyFrom

public final void copyFrom(float[] src)

copyFrom

public final void copyFrom(TensorBase src)

numDimensions

public final int numDimensions()

Rank corresponds to number of dimensions in tensor.

Specified by:

numDimensions in interface Tensor

Returns:

shape

public Shape shape()

Description copied from interface: Tensor

Returns the shape of this tensor.

Specified by:

shape in interface Tensor

Returns:

numElements

public final int numElements()

Total number of values in tensor.

Returns:

toString

public String toString()

Overrides:

toString in class Object

add

public final TensorBase add(TensorBase t)

Adds specified tensor t to this tensor.

Parameters:

t - tensor to add

addInto

public final TensorBase addInto(TensorBase t,
 TensorBase result)

add

public final void add(float val)

sub

public final void sub(TensorBase t)

Subtracts specified tensor t from this tensor.

Parameters:

t - tensor to subtract

subInto

public final TensorBase subInto(TensorBase t,
 TensorBase result)

sub

public final void sub(float val)

subInplace

public static final void subInplace(TensorBase t1,
 TensorBase t2)

Subtracts tensor t2 from t1. The result is stored in t1.

Parameters:

t1 -

t2 -

div

public final void div(float value)

Divide all values in this tensor with specified value.

Parameters:

value -

div

public final void div(float[] divisors)

fill

public final void fill(float value)

Fills the entire tensor with specified value.

Parameters:

value - value used to fill tensor

div

public final void div(TensorBase t)

Element-wise divison with specified tensor.

Parameters:

t -

copy

public TensorBase copy()

apply

public void apply(Function<Float,Float> f)

Applies specified function to all elements in tensor in-place.

Parameters:

f - function to apply to all elements.

apply

public TensorBase apply(ActivationFunction af)

equals

public boolean equals(Object obj)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object

equals

public boolean equals(TensorBase t2,
 float delta)

valuesAsString

public static String valuesAsString(TensorBase[] tensors)

setValuesFromString

public void setValuesFromString(String values)

Sets tensor values from CSV string.

Parameters:

values - string with comma separated tensor values

setValuesFromStringTransposed

public void setValuesFromStringTransposed(String values)

sum

public float sum()

sumAbs

public float sumAbs()

Returns sum of abs values of this tensor - L1 norm

Returns:

L1 norm

sumSqr

public float sumSqr()

Returns sum of squared values of this tensor - L2 norm

Returns:

L2 norm

randomize

public void randomize()

Randomize all values in tensor

multiplyElementWise

public void multiplyElementWise(TensorBase tensor2)

multiply

public TensorBase multiply(float m)

Multiplies all the values in tensor with a specified input parameter.

Parameters:

m - a multiplier for all values in tensor

multiply

public void multiply(float mul,
 int idx)

sqrt

public void sqrt()

sqr

public TensorBase sqr()

mean

public float mean()

std

public float std(float mean)

replace

public void replace(float toReplace,
 float replaceWith)

getOrCreateAccBridge

public TensorAcceleratorBridge getOrCreateAccBridge()

createAcceleratorBridge

public TensorAcceleratorBridge createAcceleratorBridge()

getAcceleratorBridge

public TensorAcceleratorBridge getAcceleratorBridge()

copyToGPU

public void copyToGPU()

copyFromGPU

public void copyFromGPU()