Interface FeatureNoiseSigma.NoiseSigmaForFeatureOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
FeatureNoiseSigma.NoiseSigmaForFeature, FeatureNoiseSigma.NoiseSigmaForFeature.Builder
Enclosing class:
FeatureNoiseSigma

public static interface FeatureNoiseSigma.NoiseSigmaForFeatureOrBuilder extends com.google.protobuf.MessageOrBuilder
  • Method Summary

    Modifier and Type
    Method
    Description
    The name of the input feature for which noise sigma is provided.
    com.google.protobuf.ByteString
    The name of the input feature for which noise sigma is provided.
    float
    This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients.

    Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

    isInitialized

    Methods inherited from interface com.google.protobuf.MessageOrBuilder

    findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof
  • Method Details

    • getName

      String getName()
       The name of the input feature for which noise sigma is provided. The
       features are defined in
       [explanation metadata
       inputs][google.cloud.aiplatform.v1.ExplanationMetadata.inputs].
       
      string name = 1;
      Returns:
      The name.
    • getNameBytes

      com.google.protobuf.ByteString getNameBytes()
       The name of the input feature for which noise sigma is provided. The
       features are defined in
       [explanation metadata
       inputs][google.cloud.aiplatform.v1.ExplanationMetadata.inputs].
       
      string name = 1;
      Returns:
      The bytes for name.
    • getSigma

      float getSigma()
       This represents the standard deviation of the Gaussian kernel that will
       be used to add noise to the feature prior to computing gradients. Similar
       to [noise_sigma][google.cloud.aiplatform.v1.SmoothGradConfig.noise_sigma]
       but represents the noise added to the current feature. Defaults to 0.1.
       
      float sigma = 2;
      Returns:
      The sigma.