com.google.cloud.aiplatform.v1beta1

Interface SmoothGradConfigOrBuilder

All Superinterfaces:

com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder

All Known Implementing Classes:

SmoothGradConfig, SmoothGradConfig.Builder

public interface SmoothGradConfigOrBuilder
extends com.google.protobuf.MessageOrBuilder

Method Summary

Modifier and Type	Method and Description
FeatureNoiseSigma	getFeatureNoiseSigma() This is similar to [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma], but provides additional flexibility.
FeatureNoiseSigmaOrBuilder	getFeatureNoiseSigmaOrBuilder() This is similar to [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma], but provides additional flexibility.
SmoothGradConfig.GradientNoiseSigmaCase	getGradientNoiseSigmaCase()
float	getNoiseSigma() This is a single float value and will be used to add noise to all the features.
int	getNoisySampleCount() The number of gradient samples to use for approximation.
boolean	hasFeatureNoiseSigma() This is similar to [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma], but provides additional flexibility.
boolean	hasNoiseSigma() This is a single float value and will be used to add noise to all the features.

Methods inherited from interface com.google.protobuf.MessageOrBuilder

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

Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

isInitialized

Method Detail

hasNoiseSigma

boolean hasNoiseSigma()

 This is a single float value and will be used to add noise to all the
 features. Use this field when all features are normalized to have the
 same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where
 features are normalized to have 0-mean and 1-variance. Learn more about
 [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization).

 For best results the recommended value is about 10% - 20% of the standard
 deviation of the input feature. Refer to section 3.2 of the SmoothGrad
 paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.

 If the distribution is different per feature, set
 [feature_noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.feature_noise_sigma]
 instead for each feature.
 

float noise_sigma = 1;

Returns:

Whether the noiseSigma field is set.

getNoiseSigma

float getNoiseSigma()

 This is a single float value and will be used to add noise to all the
 features. Use this field when all features are normalized to have the
 same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where
 features are normalized to have 0-mean and 1-variance. Learn more about
 [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization).

 For best results the recommended value is about 10% - 20% of the standard
 deviation of the input feature. Refer to section 3.2 of the SmoothGrad
 paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.

 If the distribution is different per feature, set
 [feature_noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.feature_noise_sigma]
 instead for each feature.
 

float noise_sigma = 1;

Returns:

The noiseSigma.

hasFeatureNoiseSigma

boolean hasFeatureNoiseSigma()

 This is similar to
 [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma],
 but provides additional flexibility. A separate noise sigma can be
 provided for each feature, which is useful if their distributions are
 different. No noise is added to features that are not set. If this field
 is unset,
 [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma]
 will be used for all features.
 

.google.cloud.aiplatform.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns:

Whether the featureNoiseSigma field is set.

getFeatureNoiseSigma

FeatureNoiseSigma getFeatureNoiseSigma()

 This is similar to
 [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma],
 but provides additional flexibility. A separate noise sigma can be
 provided for each feature, which is useful if their distributions are
 different. No noise is added to features that are not set. If this field
 is unset,
 [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma]
 will be used for all features.
 

.google.cloud.aiplatform.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns:

The featureNoiseSigma.

getFeatureNoiseSigmaOrBuilder

FeatureNoiseSigmaOrBuilder getFeatureNoiseSigmaOrBuilder()

 This is similar to
 [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma],
 but provides additional flexibility. A separate noise sigma can be
 provided for each feature, which is useful if their distributions are
 different. No noise is added to features that are not set. If this field
 is unset,
 [noise_sigma][google.cloud.aiplatform.v1beta1.SmoothGradConfig.noise_sigma]
 will be used for all features.
 

.google.cloud.aiplatform.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

getNoisySampleCount

int getNoisySampleCount()

 The number of gradient samples to use for
 approximation. The higher this number, the more accurate the gradient
 is, but the runtime complexity increases by this factor as well.
 Valid range of its value is [1, 50]. Defaults to 3.
 

int32 noisy_sample_count = 3;

Returns:

The noisySampleCount.

getGradientNoiseSigmaCase

SmoothGradConfig.GradientNoiseSigmaCase getGradientNoiseSigmaCase()