ExplanationMetadata_InputMetadata_Visualization_Polarity class final

Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.

Constructors

ExplanationMetadata_InputMetadata_Visualization_Polarity(String value)

const

ExplanationMetadata_InputMetadata_Visualization_Polarity.fromJson(Object? json)

factory

Properties

hashCode → int

The hash code for this object.

no setter, inherited

isNotDefault → bool

no setter

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

value → String

final, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toJson() → Object?

inherited

toString() → String

A string representation of this object.

override

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Constants

$default → const ExplanationMetadata_InputMetadata_Visualization_Polarity

The default value for ExplanationMetadata_InputMetadata_Visualization_Polarity.

both → const ExplanationMetadata_InputMetadata_Visualization_Polarity

Shows both positive and negative attributions.

negative → const ExplanationMetadata_InputMetadata_Visualization_Polarity

Setting polarity to negative highlights areas that does not lead to the models's current prediction.

polarityUnspecified → const ExplanationMetadata_InputMetadata_Visualization_Polarity

Default value. This is the same as POSITIVE.

positive → const ExplanationMetadata_InputMetadata_Visualization_Polarity

Highlights the pixels/outlines that were most influential to the model's prediction.