Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization (v0.35.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization.

Visualization configurations for image explanation.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#clip_percent_lowerbound

def clip_percent_lowerbound() -> ::Float
Returns
  • (::Float) — Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.

#clip_percent_lowerbound=

def clip_percent_lowerbound=(value) -> ::Float
Parameter
  • value (::Float) — Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
Returns
  • (::Float) — Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.

#clip_percent_upperbound

def clip_percent_upperbound() -> ::Float
Returns
  • (::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.

#clip_percent_upperbound=

def clip_percent_upperbound=(value) -> ::Float
Parameter
  • value (::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.
Returns
  • (::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.

#color_map

def color_map() -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::ColorMap
Returns
  • (::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::ColorMap) — 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.

#color_map=

def color_map=(value) -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::ColorMap
Parameter
  • value (::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::ColorMap) — 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.

Returns
  • (::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::ColorMap) — 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.

#overlay_type

def overlay_type() -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::OverlayType
Returns

#overlay_type=

def overlay_type=(value) -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::OverlayType
Parameter
Returns

#polarity

def polarity() -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::Polarity
Returns

#polarity=

def polarity=(value) -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::Polarity
Parameter
Returns

#type

def type() -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::Type
Returns

#type=

def type=(value) -> ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata::Visualization::Type
Parameter
Returns