Interface SmoothGradConfigOrBuilder (3.9.0)

public interface SmoothGradConfigOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getFeatureNoiseSigma()

public abstract FeatureNoiseSigma getFeatureNoiseSigma()

This is similar to 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 will be used for all features.

.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
TypeDescription
FeatureNoiseSigma

The featureNoiseSigma.

getFeatureNoiseSigmaOrBuilder()

public abstract FeatureNoiseSigmaOrBuilder getFeatureNoiseSigmaOrBuilder()

This is similar to 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 will be used for all features.

.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
TypeDescription
FeatureNoiseSigmaOrBuilder

getGradientNoiseSigmaCase()

public abstract SmoothGradConfig.GradientNoiseSigmaCase getGradientNoiseSigmaCase()
Returns
TypeDescription
SmoothGradConfig.GradientNoiseSigmaCase

getNoiseSigma()

public abstract 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. 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 instead for each feature.

float noise_sigma = 1;

Returns
TypeDescription
float

The noiseSigma.

getNoisySampleCount()

public abstract 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
TypeDescription
int

The noisySampleCount.

hasFeatureNoiseSigma()

public abstract boolean hasFeatureNoiseSigma()

This is similar to 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 will be used for all features.

.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
TypeDescription
boolean

Whether the featureNoiseSigma field is set.

hasNoiseSigma()

public abstract 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. 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 instead for each feature.

float noise_sigma = 1;

Returns
TypeDescription
boolean

Whether the noiseSigma field is set.