Interface ExplanationMetadata.InputMetadata.VisualizationOrBuilder (3.5.0)

Version 3.5.0

• 3.52.0 (latest)
• 3.50.0
• 3.49.0
• 3.48.0
• 3.47.0
• 3.46.0
• 3.45.0
• 3.44.0
• 3.43.0
• 3.42.0
• 3.41.0
• 3.40.0
• 3.38.0
• 3.37.0
• 3.36.0
• 3.35.0
• 3.34.0
• 3.33.0
• 3.32.0
• 3.31.0
• 3.30.0
• 3.29.0
• 3.28.0
• 3.25.0
• 3.24.0
• 3.23.0
• 3.22.0
• 3.21.0
• 3.20.0
• 3.19.0
• 3.18.0
• 3.17.0
• 3.16.0
• 3.15.0
• 3.14.0
• 3.13.0
• 3.12.0
• 3.11.0
• 3.10.0
• 3.9.0
• 3.8.0
• 3.7.0
• 3.6.0
• 3.5.0
• 3.4.2
• 3.3.0
• 3.2.0
• 3.0.0
• 2.9.8
• 2.8.9
• 2.7.4
• 2.5.3
• 2.4.0

public static interface ExplanationMetadata.InputMetadata.VisualizationOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getClipPercentLowerbound()

public abstract float getClipPercentLowerbound()

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

float clip_percent_lowerbound = 5;

Returns

Type	Description
float	The clipPercentLowerbound.

getClipPercentUpperbound()

public abstract float getClipPercentUpperbound()

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.

float clip_percent_upperbound = 4;

Returns

Type	Description
float	The clipPercentUpperbound.

getColorMap()

public abstract ExplanationMetadata.InputMetadata.Visualization.ColorMap getColorMap()

The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.ColorMap color_map = 3;

Returns

Type	Description
ExplanationMetadata.InputMetadata.Visualization.ColorMap	The colorMap.

getColorMapValue()

public abstract int getColorMapValue()

The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.ColorMap color_map = 3;

Returns

Type	Description
int	The enum numeric value on the wire for colorMap.

getOverlayType()

public abstract ExplanationMetadata.InputMetadata.Visualization.OverlayType getOverlayType()

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.

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.OverlayType overlay_type = 6;

Returns

Type	Description
ExplanationMetadata.InputMetadata.Visualization.OverlayType	The overlayType.

getOverlayTypeValue()

public abstract int getOverlayTypeValue()

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.

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.OverlayType overlay_type = 6;

Returns

Type	Description
int	The enum numeric value on the wire for overlayType.

getPolarity()

public abstract ExplanationMetadata.InputMetadata.Visualization.Polarity getPolarity()

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

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.Polarity polarity = 2;

Returns

Type	Description
ExplanationMetadata.InputMetadata.Visualization.Polarity	The polarity.

getPolarityValue()

public abstract int getPolarityValue()

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

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.Polarity polarity = 2;

Returns

Type	Description
int	The enum numeric value on the wire for polarity.

getType()

public abstract ExplanationMetadata.InputMetadata.Visualization.Type getType()

Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.Type type = 1;

Returns

Type	Description
ExplanationMetadata.InputMetadata.Visualization.Type	The type.

getTypeValue()

public abstract int getTypeValue()

Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.

.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization.Type type = 1;

Returns

Type	Description
int	The enum numeric value on the wire for type.