SparseCategoricalCrossEntropy

Instance Constructors

new SparseCategoricalCrossEntropy(logProbAsInput: Boolean = false, zeroBasedLabel: Boolean = true, weights: Tensor[T] = null, sizeAverage: Boolean = true, paddingValue: Int = 1)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

logProbAsInput
Boolean. Whether to accept log-probabilities or probabilities as input. Default is false and inputs should be probabilities.
zeroBasedLabel
Boolean. Whether target labels start from 0. Default is true. If false, labels start from 1.
weights
Tensor. Weights of each class if you have an unbalanced training set. Default is null.
sizeAverage
Boolean. Whether losses are averaged over observations for each mini-batch. Default is true. If false, the losses are instead summed for each mini-batch.
paddingValue
Integer. If the target is set to this value, the training process will skip this sample. In other words, the forward process will return zero output and the backward process will also return zero gradInput. Default is -1.

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
def backward(input: Tensor[T], target: Tensor[T]): Tensor[T]

Definition Classes
AbstractCriterion
def canEqual(other: Any): Boolean

Definition Classes
AbstractCriterion
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def cloneCriterion(): AbstractCriterion[Tensor[T], Tensor[T], T]

Definition Classes
AbstractCriterion
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(other: Any): Boolean

Definition Classes
AbstractCriterion → AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def forward(input: Tensor[T], target: Tensor[T]): T

Definition Classes
AbstractCriterion
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
var gradInput: Tensor[T]

Definition Classes
AbstractCriterion
def hashCode(): Int

Definition Classes
AbstractCriterion → AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
val logProbAsInput: Boolean

Boolean.
Boolean. Whether to accept log-probabilities or probabilities as input. Default is false and inputs should be probabilities.
val loss: TensorCriterion[T]

Definition Classes
SparseCategoricalCrossEntropy → LossFunction
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
var output: T

Definition Classes
AbstractCriterion
val paddingValue: Int

Integer.
Integer. If the target is set to this value, the training process will skip this sample. In other words, the forward process will return zero output and the backward process will also return zero gradInput. Default is -1.
val sizeAverage: Boolean

Boolean.
Boolean. Whether losses are averaged over observations for each mini-batch. Default is true. If false, the losses are instead summed for each mini-batch.
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
def updateGradInput(input: Tensor[T], target: Tensor[T]): Tensor[T]

Definition Classes
SparseCategoricalCrossEntropy → LossFunction → AbstractCriterion
def updateOutput(input: Tensor[T], target: Tensor[T]): T

Definition Classes
SparseCategoricalCrossEntropy → LossFunction → AbstractCriterion
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
val weights: Tensor[T]

Tensor.
Tensor. Weights of each class if you have an unbalanced training set. Default is null.
val zeroBasedLabel: Boolean

Boolean.
Boolean. Whether target labels start from 0. Default is true. If false, labels start from 1.

Related Docs: object SparseCategoricalCrossEntropy | package objectives

class SparseCategoricalCrossEntropy[T] extends TensorLossFunction[T]

Instance Constructors

new SparseCategoricalCrossEntropy(logProbAsInput: Boolean = false, zeroBasedLabel: Boolean = true, weights: Tensor[T] = null, sizeAverage: Boolean = true, paddingValue: Int = 1)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def backward(input: Tensor[T], target: Tensor[T]): Tensor[T]

def canEqual(other: Any): Boolean

def clone(): AnyRef

def cloneCriterion(): AbstractCriterion[Tensor[T], Tensor[T], T]

final def eq(arg0: AnyRef): Boolean

def equals(other: Any): Boolean

def finalize(): Unit

def forward(input: Tensor[T], target: Tensor[T]): T

final def getClass(): Class[_]

var gradInput: Tensor[T]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

val logProbAsInput: Boolean

val loss: TensorCriterion[T]

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

var output: T

val paddingValue: Int

val sizeAverage: Boolean

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

def updateGradInput(input: Tensor[T], target: Tensor[T]): Tensor[T]

def updateOutput(input: Tensor[T], target: Tensor[T]): T

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

val weights: Tensor[T]

val zeroBasedLabel: Boolean

Inherited from TensorLossFunction[T]

Inherited from LossFunction[Tensor[T], Tensor[T], T]

Inherited from AbstractCriterion[Tensor[T], Tensor[T], T]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped