Class SmoothGradConfig.Builder (3.84.0)

Version latest

• 3.84.0 (latest)
• 3.83.0
• 3.82.0
• 3.81.0
• 3.79.0
• 3.77.0
• 3.76.0
• 3.75.0
• 3.74.0
• 3.73.0
• 3.71.0
• 3.69.0
• 3.68.0
• 3.65.0
• 3.64.0
• 3.63.0
• 3.61.0
• 3.60.0
• 3.59.0
• 3.58.0
• 3.57.0
• 3.56.0
• 3.55.0
• 3.54.0
• 3.53.0
• 3.52.0
• 3.50.0
• 3.49.0
• 3.48.0
• 3.47.0
• 3.46.0
• 3.45.0
• 3.44.0
• 3.43.0
• 3.42.0
• 3.41.0
• 3.40.0
• 3.38.0
• 3.37.0
• 3.36.0
• 3.35.0
• 3.34.0
• 3.33.0
• 3.32.0
• 3.31.0
• 3.30.0
• 3.29.0
• 3.28.0
• 3.25.0
• 3.24.0
• 3.23.0
• 3.22.0
• 3.21.0
• 3.20.0
• 3.19.0
• 3.18.0
• 3.17.0
• 3.16.0
• 3.15.0
• 3.14.0
• 3.13.0
• 3.12.0
• 3.11.0
• 3.10.0
• 3.9.0
• 3.8.0
• 3.7.0
• 3.6.0
• 3.5.0
• 3.4.2
• 3.3.0
• 3.2.0
• 3.0.0
• 2.9.8
• 2.8.9
• 2.7.4
• 2.5.3
• 2.4.0

public static final class SmoothGradConfig.Builder extends GeneratedMessage.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.v1beta1.SmoothGradConfig

Inheritance

java.lang.Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessage.Builder > SmoothGradConfig.Builder

Implements

SmoothGradConfigOrBuilder

Inherited Members

AbstractMessage.Builder.findInitializationErrors()

AbstractMessage.Builder.getInitializationErrorString()

AbstractMessage.Builder.internalMergeFrom(AbstractMessageLite)

AbstractMessage.Builder.mergeFrom(byte[])

AbstractMessage.Builder.mergeFrom(byte[],ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(byte[],int,int)

AbstractMessage.Builder.mergeFrom(byte[],int,int,ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(ByteString)

AbstractMessage.Builder.mergeFrom(ByteString,ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(CodedInputStream)

AbstractMessage.Builder.mergeFrom(CodedInputStream,ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(Message)

AbstractMessage.Builder.mergeFrom(InputStream)

AbstractMessage.Builder.mergeFrom(InputStream,ExtensionRegistryLite)

AbstractMessage.Builder.newUninitializedMessageException(Message)

AbstractMessage.Builder.toString()

AbstractMessageLite.Builder.<T>addAll(Iterable<T>,Collection<? super T>)

AbstractMessageLite.Builder.<T>addAll(Iterable<T>,List<? super T>)

AbstractMessageLite.Builder.internalMergeFrom(MessageType)

AbstractMessageLite.Builder.mergeDelimitedFrom(InputStream)

AbstractMessageLite.Builder.mergeDelimitedFrom(InputStream,ExtensionRegistryLite)

AbstractMessageLite.Builder.mergeFrom(MessageLite)

AbstractMessageLite.Builder.newUninitializedMessageException(MessageLite)

GeneratedMessage.Builder.addRepeatedField(Descriptors.FieldDescriptor,Object)

GeneratedMessage.Builder.clear()

GeneratedMessage.Builder.clearField(Descriptors.FieldDescriptor)

GeneratedMessage.Builder.clearOneof(Descriptors.OneofDescriptor)

GeneratedMessage.Builder.clone()

GeneratedMessage.Builder.getAllFields()

GeneratedMessage.Builder.getDescriptorForType()

GeneratedMessage.Builder.getField(Descriptors.FieldDescriptor)

GeneratedMessage.Builder.getFieldBuilder(Descriptors.FieldDescriptor)

GeneratedMessage.Builder.getOneofFieldDescriptor(Descriptors.OneofDescriptor)

GeneratedMessage.Builder.getParentForChildren()

GeneratedMessage.Builder.getRepeatedField(Descriptors.FieldDescriptor,int)

GeneratedMessage.Builder.getRepeatedFieldBuilder(Descriptors.FieldDescriptor,int)

GeneratedMessage.Builder.getRepeatedFieldCount(Descriptors.FieldDescriptor)

com.google.protobuf.GeneratedMessage.Builder.getUnknownFieldSetBuilder()

GeneratedMessage.Builder.getUnknownFields()

GeneratedMessage.Builder.hasField(Descriptors.FieldDescriptor)

GeneratedMessage.Builder.hasOneof(Descriptors.OneofDescriptor)

GeneratedMessage.Builder.internalGetFieldAccessorTable()

GeneratedMessage.Builder.internalGetMapField(int)

com.google.protobuf.GeneratedMessage.Builder.internalGetMapFieldReflection(int)

GeneratedMessage.Builder.internalGetMutableMapField(int)

com.google.protobuf.GeneratedMessage.Builder.internalGetMutableMapFieldReflection(int)

GeneratedMessage.Builder.isClean()

GeneratedMessage.Builder.isInitialized()

GeneratedMessage.Builder.markClean()

GeneratedMessage.Builder.mergeUnknownFields(UnknownFieldSet)

com.google.protobuf.GeneratedMessage.Builder.mergeUnknownLengthDelimitedField(int,com.google.protobuf.ByteString)

com.google.protobuf.GeneratedMessage.Builder.mergeUnknownVarintField(int,int)

GeneratedMessage.Builder.newBuilderForField(Descriptors.FieldDescriptor)

GeneratedMessage.Builder.onBuilt()

GeneratedMessage.Builder.onChanged()

com.google.protobuf.GeneratedMessage.Builder.parseUnknownField(com.google.protobuf.CodedInputStream,com.google.protobuf.ExtensionRegistryLite,int)

GeneratedMessage.Builder.setField(Descriptors.FieldDescriptor,Object)

GeneratedMessage.Builder.setRepeatedField(Descriptors.FieldDescriptor,int,Object)

com.google.protobuf.GeneratedMessage.Builder.setUnknownFieldSetBuilder(com.google.protobuf.UnknownFieldSet.Builder)

GeneratedMessage.Builder.setUnknownFields(UnknownFieldSet)

com.google.protobuf.GeneratedMessage.Builder.setUnknownFieldsProto3(com.google.protobuf.UnknownFieldSet)

Object.equals(Object)

Object.finalize()

Object.getClass()

Object.hashCode()

Object.notify()

Object.notifyAll()

Object.wait()

Object.wait(long)

Object.wait(long,int)

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()

Returns
Type	Description
Descriptor

Methods

build()

public SmoothGradConfig build()

Returns
Type	Description
SmoothGradConfig

buildPartial()

public SmoothGradConfig buildPartial()

Returns
Type	Description
SmoothGradConfig

clear()

public SmoothGradConfig.Builder clear()

Returns
Type	Description
SmoothGradConfig.Builder

Overrides

GeneratedMessage.Builder<BuilderType>.clear()

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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
Type	Description
SmoothGradConfig.Builder

clearGradientNoiseSigma()

public SmoothGradConfig.Builder clearGradientNoiseSigma()

Returns
Type	Description
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
Type	Description
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
Type	Description
SmoothGradConfig.Builder	This builder for chaining.

getDefaultInstanceForType()

public SmoothGradConfig getDefaultInstanceForType()

Returns
Type	Description
SmoothGradConfig

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()

Returns
Type	Description
Descriptor

Overrides

GeneratedMessage.Builder<BuilderType>.getDescriptorForType()

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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
Type	Description
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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
Type	Description
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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
Type	Description
FeatureNoiseSigmaOrBuilder

getGradientNoiseSigmaCase()

public SmoothGradConfig.GradientNoiseSigmaCase getGradientNoiseSigmaCase()

Returns
Type	Description
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
Type	Description
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
Type	Description
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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Returns
Type	Description
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
Type	Description
boolean	Whether the noiseSigma field is set.

internalGetFieldAccessorTable()

protected GeneratedMessage.FieldAccessorTable internalGetFieldAccessorTable()

Returns
Type	Description
FieldAccessorTable

Overrides

GeneratedMessage.Builder<BuilderType>.internalGetFieldAccessorTable()

isInitialized()

public final boolean isInitialized()

Returns
Type	Description
boolean

Overrides

GeneratedMessage.Builder<BuilderType>.isInitialized()

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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Parameter
Name	Description
value	FeatureNoiseSigma

Returns
Type	Description
SmoothGradConfig.Builder

mergeFrom(SmoothGradConfig other)

public SmoothGradConfig.Builder mergeFrom(SmoothGradConfig other)

Parameter
Name	Description
other	SmoothGradConfig

Returns
Type	Description
SmoothGradConfig.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public SmoothGradConfig.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

Parameters
Name	Description
input	CodedInputStream
extensionRegistry	ExtensionRegistryLite

Returns
Type	Description
SmoothGradConfig.Builder

Overrides

AbstractMessage.Builder<BuilderType>.mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

Exceptions
Type	Description
IOException

mergeFrom(Message other)

public SmoothGradConfig.Builder mergeFrom(Message other)

Parameter
Name	Description
other	Message

Returns
Type	Description
SmoothGradConfig.Builder

Overrides

AbstractMessage.Builder<BuilderType>.mergeFrom(Message other)

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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Parameter
Name	Description
value	FeatureNoiseSigma

Returns
Type	Description
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.v1beta1.FeatureNoiseSigma feature_noise_sigma = 2;

Parameter
Name	Description
builderForValue	FeatureNoiseSigma.Builder

Returns
Type	Description
SmoothGradConfig.Builder

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
Name	Description
value	float The noiseSigma to set.

Returns
Type	Description
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
Name	Description
value	int The noisySampleCount to set.

Returns
Type	Description
SmoothGradConfig.Builder	This builder for chaining.