Class ExplanationMetadata.Types.InputMetadata.Types.Visualization

public sealed class Visualization : IMessage<ExplanationMetadata.Types.InputMetadata.Types.Visualization>, IEquatable<ExplanationMetadata.Types.InputMetadata.Types.Visualization>, IDeepCloneable<ExplanationMetadata.Types.InputMetadata.Types.Visualization>, IBufferMessage, IMessage

Visualization configurations for image explanation.

Inheritance

Object > ExplanationMetadata.Types.InputMetadata.Types.Visualization

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

Visualization()

public Visualization()

Visualization(ExplanationMetadata.Types.InputMetadata.Types.Visualization)

public Visualization(ExplanationMetadata.Types.InputMetadata.Types.Visualization other)
Parameter
NameDescription
otherExplanationMetadata.Types.InputMetadata.Types.Visualization

Properties

ClipPercentLowerbound

public float ClipPercentLowerbound { get; set; }

Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.

Property Value
TypeDescription
Single

ClipPercentUpperbound

public float ClipPercentUpperbound { get; set; }

Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.

Property Value
TypeDescription
Single

ColorMap

public ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.ColorMap ColorMap { get; set; }

The color scheme used for the highlighted areas.

Defaults to PINK_GREEN for [Integrated Gradients attribution][google.cloud.aiplatform.v1.ExplanationParameters.integrated_gradients_attribution], which shows positive attributions in green and negative in pink.

Defaults to VIRIDIS for [XRAI attribution][google.cloud.aiplatform.v1.ExplanationParameters.xrai_attribution], which highlights the most influential regions in yellow and the least influential in blue.

Property Value
TypeDescription
ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.ColorMap

OverlayType

public ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.OverlayType OverlayType { get; set; }

How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.

Property Value
TypeDescription
ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.OverlayType

Polarity

public ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.Polarity Polarity { get; set; }

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

Property Value
TypeDescription
ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.Polarity

Type

public ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.Type Type { get; set; }

Type of the image visualization. Only applicable to [Integrated Gradients attribution][google.cloud.aiplatform.v1.ExplanationParameters.integrated_gradients_attribution]. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.

Property Value
TypeDescription
ExplanationMetadata.Types.InputMetadata.Types.Visualization.Types.Type