Class Losses

A loss function (or objective function, or optimization score function) is one of the two parameters required to compile a model

Inheritance

System.Object

Keras

Base

Losses

Implements

System.IDisposable

Inherited Members

Base.Parameters

Base.None

Base.Init()

Base.ToPython()

Base.InvokeStaticMethod(Object, String, Dictionary<String, Object>)

Base.InvokeMethod(String, Dictionary<String, Object>)

Base.Item[String]

Keras.Instance

Keras.keras

Keras.keras2onnx

Keras.tfjs

Keras.Dispose()

Keras.ToTuple(Array)

Keras.ToList(Array)

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: Keras

Assembly: Keras.dll

Syntax

public class Losses : Base, IDisposable

Methods

| Improve this Doc View Source

BinaryCrossentropy(NDarray, NDarray)

Binaries the crossentropy.

Declaration

public static NDarray BinaryCrossentropy(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

CategoricalCrossentropy(NDarray, NDarray)

Categoricals the crossentropy.

Declaration

public static NDarray CategoricalCrossentropy(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

CategoricalHinge(NDarray, NDarray)

Calculates the categorial hinge.

Declaration

public static NDarray CategoricalHinge(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

CosineProximity(NDarray, NDarray)

Cosines the proximity.

Declaration

public static NDarray CosineProximity(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

Hinge(NDarray, NDarray)

Calculates the Hinge error.

Declaration

public static NDarray Hinge(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

KullbackLeiblerDivergence(NDarray, NDarray)

Kullbacks the leibler divergence.

Declaration

public static NDarray KullbackLeiblerDivergence(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

LogCosh(NDarray, NDarray)

Logarithm of the hyperbolic cosine of the prediction error. log(cosh(x)) is approximately equal to(x** 2) / 2 for small x and to abs(x) - log(2) for large x.This means that 'logcosh' works mostly like the mean squared error, but will not be so strongly affected by the occasional wildly incorrect prediction.

Declaration

public static NDarray LogCosh(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

MeanAbsoluteError(NDarray, NDarray)

Calculates the mean absolute error.

Declaration

public static NDarray MeanAbsoluteError(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

MeanAbsolutePercentageError(NDarray, NDarray)

Calculates the mean absolute percentage error.

Declaration

public static NDarray MeanAbsolutePercentageError(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

MeanSquaredError(NDarray, NDarray)

Calculates the mean squared error.

Declaration

public static NDarray MeanSquaredError(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

MeanSquaredLogarithmicError(NDarray, NDarray)

Calculates the mean squared log error.

Declaration

public static NDarray MeanSquaredLogarithmicError(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

Poisson(NDarray, NDarray)

Poissons the specified y true.

Declaration

public static NDarray Poisson(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

SparseCategoricalCrossentropy(NDarray, NDarray)

Sparses the categorical crossentropy.

Declaration

public static NDarray SparseCategoricalCrossentropy(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

| Improve this Doc View Source

SquaredHinge(NDarray, NDarray)

Calculates the Square Hinge

Declaration

public static NDarray SquaredHinge(NDarray y_true, NDarray y_pred)

Parameters

Type	Name	Description
Numpy.NDarray	y_true	tensor of true targets.
Numpy.NDarray	y_pred	tensor of predicted targets.

Returns

Type	Description
Numpy.NDarray

Implements

System.IDisposable