Interface Loss

All Superinterfaces:

BiFunction<Tensor,Tensor,Tensor>

public interface Loss
extends BiFunction<Tensor,Tensor,Tensor>

Loss functions.

Method Summary

Static Methods

Modifier and Type	Method	Description
static Loss	crossEntropy()	Cross Entropy Loss Function.
static Loss	hingeEmbedding()	Hinge Embedding Loss Function.
static Loss	kl()	Kullback-Leibler Divergence Loss Function.
static Loss	l1()	Mean Absolute Error (L1) Loss Function.
static Tensor	marginRanking(Tensor input1, Tensor input2, Tensor target)	Margin Ranking Loss Function.
static Loss	mse()	Mean Squared Error (L2) Loss Function.
static Loss	nll()	Negative Log-Likelihood Loss Function.
static Tensor	tripleMarginRanking(Tensor anchor, Tensor positive, Tensor negative)	Triplet Margin Ranking Loss Function.

Methods inherited from interface BiFunction

andThen, apply

Method Details

l1

static Loss l1()

Mean Absolute Error (L1) Loss Function.

Returns:

the loss functor.

mse

static Loss mse()

Mean Squared Error (L2) Loss Function.

Returns:

the loss functor.

nll

static Loss nll()

Negative Log-Likelihood Loss Function.

Returns:

the loss functor.

crossEntropy

static Loss crossEntropy()

Cross Entropy Loss Function.

Returns:

the loss functor.

hingeEmbedding

static Loss hingeEmbedding()

Hinge Embedding Loss Function.

Returns:

the loss functor.

kl

static Loss kl()

Kullback-Leibler Divergence Loss Function.

Returns:

the loss functor.

marginRanking

static Tensor marginRanking(Tensor input1,
 Tensor input2,
 Tensor target)

Margin Ranking Loss Function.

Parameters:

input1 - the first input.

input2 - the second input.

target - the target/truth.

Returns:

the loss.

tripleMarginRanking

static Tensor tripleMarginRanking(Tensor anchor,
 Tensor positive,
 Tensor negative)

Triplet Margin Ranking Loss Function.

Parameters:

anchor - the first input.

positive - the second input.

negative - the third input.

Returns:

the loss.