Class SmoothGradConfig (2.5.3)

public final class SmoothGradConfig extends GeneratedMessageV3 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

Fields

FEATURE_NOISE_SIGMA_FIELD_NUMBER

public static final int FEATURE_NOISE_SIGMA_FIELD_NUMBER
Field Value
TypeDescription
int

NOISE_SIGMA_FIELD_NUMBER

public static final int NOISE_SIGMA_FIELD_NUMBER
Field Value
TypeDescription
int

NOISY_SAMPLE_COUNT_FIELD_NUMBER

public static final int NOISY_SAMPLE_COUNT_FIELD_NUMBER
Field Value
TypeDescription
int

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
NameDescription
objObject
Returns
TypeDescription
boolean
Overrides

getDefaultInstance()

public static SmoothGradConfig getDefaultInstance()
Returns
TypeDescription
SmoothGradConfig

getDefaultInstanceForType()

public SmoothGradConfig getDefaultInstanceForType()
Returns
TypeDescription
SmoothGradConfig

getDescriptor()

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

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
TypeDescription
FeatureNoiseSigma

The featureNoiseSigma.

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
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.

getParserForType()

public Parser<SmoothGradConfig> getParserForType()
Returns
TypeDescription
Parser<SmoothGradConfig>
Overrides

getSerializedSize()

public int getSerializedSize()
Returns
TypeDescription
int
Overrides

getUnknownFields()

public final UnknownFieldSet getUnknownFields()
Returns
TypeDescription
UnknownFieldSet
Overrides

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
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.

hashCode()

public int hashCode()
Returns
TypeDescription
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

newBuilder()

public static SmoothGradConfig.Builder newBuilder()
Returns
TypeDescription
SmoothGradConfig.Builder

newBuilder(SmoothGradConfig prototype)

public static SmoothGradConfig.Builder newBuilder(SmoothGradConfig prototype)
Parameter
NameDescription
prototypeSmoothGradConfig
Returns
TypeDescription
SmoothGradConfig.Builder

newBuilderForType()

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

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected SmoothGradConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
NameDescription
parentBuilderParent
Returns
TypeDescription
SmoothGradConfig.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
NameDescription
unusedUnusedPrivateParameter
Returns
TypeDescription
Object
Overrides

parseDelimitedFrom(InputStream input)

public static SmoothGradConfig parseDelimitedFrom(InputStream input)
Parameter
NameDescription
inputInputStream
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static SmoothGradConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
IOException

parseFrom(byte[] data)

public static SmoothGradConfig parseFrom(byte[] data)
Parameter
NameDescription
databyte[]
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static SmoothGradConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
databyte[]
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteString data)

public static SmoothGradConfig parseFrom(ByteString data)
Parameter
NameDescription
dataByteString
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static SmoothGradConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
dataByteString
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static SmoothGradConfig parseFrom(CodedInputStream input)
Parameter
NameDescription
inputCodedInputStream
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static SmoothGradConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
IOException

parseFrom(InputStream input)

public static SmoothGradConfig parseFrom(InputStream input)
Parameter
NameDescription
inputInputStream
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static SmoothGradConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
IOException

parseFrom(ByteBuffer data)

public static SmoothGradConfig parseFrom(ByteBuffer data)
Parameter
NameDescription
dataByteBuffer
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static SmoothGradConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
dataByteBuffer
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
SmoothGradConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parser()

public static Parser<SmoothGradConfig> parser()
Returns
TypeDescription
Parser<SmoothGradConfig>

toBuilder()

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

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
NameDescription
outputCodedOutputStream
Overrides Exceptions
TypeDescription
IOException