Class SmoothGradConfig.Builder (3.12.0)

public static final class SmoothGradConfig.Builder extends GeneratedMessageV3.Builder<SmoothGradConfig.Builder> implements SmoothGradConfigOrBuilder

Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf

Protobuf type google.cloud.aiplatform.v1.SmoothGradConfig

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
TypeDescription
Descriptor

Methods

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public SmoothGradConfig.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

build()

public SmoothGradConfig build()
Returns
TypeDescription
SmoothGradConfig

buildPartial()

public SmoothGradConfig buildPartial()
Returns
TypeDescription
SmoothGradConfig

clear()

public SmoothGradConfig.Builder clear()
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

clearFeatureNoiseSigma()

public SmoothGradConfig.Builder clearFeatureNoiseSigma()

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
SmoothGradConfig.Builder

clearField(Descriptors.FieldDescriptor field)

public SmoothGradConfig.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
NameDescription
fieldFieldDescriptor
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

clearGradientNoiseSigma()

public SmoothGradConfig.Builder clearGradientNoiseSigma()
Returns
TypeDescription
SmoothGradConfig.Builder

clearNoiseSigma()

public SmoothGradConfig.Builder clearNoiseSigma()

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
SmoothGradConfig.Builder

This builder for chaining.

clearNoisySampleCount()

public SmoothGradConfig.Builder clearNoisySampleCount()

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
SmoothGradConfig.Builder

This builder for chaining.

clearOneof(Descriptors.OneofDescriptor oneof)

public SmoothGradConfig.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
NameDescription
oneofOneofDescriptor
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

clone()

public SmoothGradConfig.Builder clone()
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

getDefaultInstanceForType()

public SmoothGradConfig getDefaultInstanceForType()
Returns
TypeDescription
SmoothGradConfig

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
TypeDescription
Descriptor
Overrides

getFeatureNoiseSigma()

public 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.

getFeatureNoiseSigmaBuilder()

public FeatureNoiseSigma.Builder getFeatureNoiseSigmaBuilder()

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.Builder

getFeatureNoiseSigmaOrBuilder()

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

getNoiseSigma()

public 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 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 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 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.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

mergeFeatureNoiseSigma(FeatureNoiseSigma value)

public SmoothGradConfig.Builder mergeFeatureNoiseSigma(FeatureNoiseSigma value)

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;

Parameter
NameDescription
valueFeatureNoiseSigma
Returns
TypeDescription
SmoothGradConfig.Builder

mergeFrom(SmoothGradConfig other)

public SmoothGradConfig.Builder mergeFrom(SmoothGradConfig other)
Parameter
NameDescription
otherSmoothGradConfig
Returns
TypeDescription
SmoothGradConfig.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public SmoothGradConfig.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides Exceptions
TypeDescription
IOException

mergeFrom(Message other)

public SmoothGradConfig.Builder mergeFrom(Message other)
Parameter
NameDescription
otherMessage
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

mergeUnknownFields(UnknownFieldSet unknownFields)

public final SmoothGradConfig.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

setFeatureNoiseSigma(FeatureNoiseSigma value)

public SmoothGradConfig.Builder setFeatureNoiseSigma(FeatureNoiseSigma value)

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;

Parameter
NameDescription
valueFeatureNoiseSigma
Returns
TypeDescription
SmoothGradConfig.Builder

setFeatureNoiseSigma(FeatureNoiseSigma.Builder builderForValue)

public SmoothGradConfig.Builder setFeatureNoiseSigma(FeatureNoiseSigma.Builder builderForValue)

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;

Parameter
NameDescription
builderForValueFeatureNoiseSigma.Builder
Returns
TypeDescription
SmoothGradConfig.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public SmoothGradConfig.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

setNoiseSigma(float value)

public SmoothGradConfig.Builder setNoiseSigma(float value)

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;

Parameter
NameDescription
valuefloat

The noiseSigma to set.

Returns
TypeDescription
SmoothGradConfig.Builder

This builder for chaining.

setNoisySampleCount(int value)

public SmoothGradConfig.Builder setNoisySampleCount(int value)

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;

Parameter
NameDescription
valueint

The noisySampleCount to set.

Returns
TypeDescription
SmoothGradConfig.Builder

This builder for chaining.

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public SmoothGradConfig.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
NameDescription
fieldFieldDescriptor
indexint
valueObject
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

setUnknownFields(UnknownFieldSet unknownFields)

public final SmoothGradConfig.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides