Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ExplanationMetadataInputMetadataVisualization

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb

Overview

Visualization configurations for image explanation.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1ExplanationMetadataInputMetadataVisualization

Returns a new instance of GoogleCloudAiplatformV1beta1ExplanationMetadataInputMetadataVisualization.



6906
6907
6908
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6906

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#clip_percent_lowerbound ⇒ Float

Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62. Corresponds to the JSON property clipPercentLowerbound

Returns:

  • (Float) 


6867
6868
6869
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6867

def clip_percent_lowerbound
  @clip_percent_lowerbound
end

#clip_percent_upperbound ⇒ Float

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. Corresponds to the JSON property clipPercentUpperbound

Returns:

  • (Float) 


6875
6876
6877
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6875

def clip_percent_upperbound
  @clip_percent_upperbound
end

#color_map ⇒ String

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. Corresponds to the JSON property colorMap

Returns:

  • (String) 


6884
6885
6886
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6884

def color_map
  @color_map
end

#overlay_type ⇒ String

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. Corresponds to the JSON property overlayType

Returns:

  • (String) 


6891
6892
6893
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6891

def overlay_type
  @overlay_type
end

#polarity ⇒ String

Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE. Corresponds to the JSON property polarity

Returns:

  • (String) 


6897
6898
6899
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6897

def polarity
  @polarity
end

#type ⇒ String

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. Corresponds to the JSON property type

Returns:

  • (String) 


6904
6905
6906
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6904

def type
  @type
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



6911
6912
6913
6914
6915
6916
6917
6918
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 6911

def update!(**args)
  @clip_percent_lowerbound = args[:clip_percent_lowerbound] if args.key?(:clip_percent_lowerbound)
  @clip_percent_upperbound = args[:clip_percent_upperbound] if args.key?(:clip_percent_upperbound)
  @color_map = args[:color_map] if args.key?(:color_map)
  @overlay_type = args[:overlay_type] if args.key?(:overlay_type)
  @polarity = args[:polarity] if args.key?(:polarity)
  @type = args[:type] if args.key?(:type)
end