Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ExplanationMetadataInputMetadata

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb

Overview

Metadata of the input of a feature. Fields other than InputMetadata. input_baselines are applicable only for Models that are using Vertex AI- provided images for Tensorflow.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1ExplanationMetadataInputMetadata

Returns a new instance of GoogleCloudAiplatformV1ExplanationMetadataInputMetadata.



7134
7135
7136
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7134

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

Instance Attribute Details

#dense_shape_tensor_name ⇒ String

Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https:// www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor. Corresponds to the JSON property denseShapeTensorName

Returns:

  • (String) 


7047
7048
7049
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7047

def dense_shape_tensor_name
  @dense_shape_tensor_name
end

#encoded_baselines ⇒ Array<Object>

A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor. Corresponds to the JSON property encodedBaselines

Returns:

  • (Array<Object>) 


7054
7055
7056
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7054

def encoded_baselines
  @encoded_baselines
end

#encoded_tensor_name ⇒ String

Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table. Corresponds to the JSON property encodedTensorName

Returns:

  • (String) 


7062
7063
7064
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7062

def encoded_tensor_name
  @encoded_tensor_name
end

#encoding ⇒ String

Defines how the feature is encoded into the input tensor. Defaults to IDENTITY. Corresponds to the JSON property encoding

Returns:

  • (String) 


7067
7068
7069
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7067

def encoding
  @encoding
end

#feature_value_domain ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ExplanationMetadataInputMetadataFeatureValueDomain

Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre- processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. Corresponds to the JSON property featureValueDomain

Returns:



7079
7080
7081
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7079

def feature_value_domain
  @feature_value_domain
end

#group_name ⇒ String

Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name. Corresponds to the JSON property groupName

Returns:

  • (String) 


7088
7089
7090
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7088

def group_name
  @group_name
end

#index_feature_mapping ⇒ Array<String>

A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR. Corresponds to the JSON property indexFeatureMapping

Returns:

  • (Array<String>) 


7095
7096
7097
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7095

def index_feature_mapping
  @index_feature_mapping
end

#indices_tensor_name ⇒ String

Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor. Corresponds to the JSON property indicesTensorName

Returns:

  • (String) 


7102
7103
7104
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7102

def indices_tensor_name
  @indices_tensor_name
end

#input_baselines ⇒ Array<Object>

Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution. feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2. x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri. Corresponds to the JSON property inputBaselines

Returns:

  • (Array<Object>) 


7116
7117
7118
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7116

def input_baselines
  @input_baselines
end

#input_tensor_name ⇒ String

Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow. Corresponds to the JSON property inputTensorName

Returns:

  • (String) 


7122
7123
7124
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7122

def input_tensor_name
  @input_tensor_name
end

#modality ⇒ String

Modality of the feature. Valid values are: numeric, image. Defaults to numeric. Corresponds to the JSON property modality

Returns:

  • (String) 


7127
7128
7129
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7127

def modality
  @modality
end

#visualization ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ExplanationMetadataInputMetadataVisualization

Visualization configurations for image explanation. Corresponds to the JSON property visualization

Returns:



7132
7133
7134
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7132

def visualization
  @visualization
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 7139

def update!(**args)
  @dense_shape_tensor_name = args[:dense_shape_tensor_name] if args.key?(:dense_shape_tensor_name)
  @encoded_baselines = args[:encoded_baselines] if args.key?(:encoded_baselines)
  @encoded_tensor_name = args[:encoded_tensor_name] if args.key?(:encoded_tensor_name)
  @encoding = args[:encoding] if args.key?(:encoding)
  @feature_value_domain = args[:feature_value_domain] if args.key?(:feature_value_domain)
  @group_name = args[:group_name] if args.key?(:group_name)
  @index_feature_mapping = args[:index_feature_mapping] if args.key?(:index_feature_mapping)
  @indices_tensor_name = args[:indices_tensor_name] if args.key?(:indices_tensor_name)
  @input_baselines = args[:input_baselines] if args.key?(:input_baselines)
  @input_tensor_name = args[:input_tensor_name] if args.key?(:input_tensor_name)
  @modality = args[:modality] if args.key?(:modality)
  @visualization = args[:visualization] if args.key?(:visualization)
end