Class SmoothGradConfig (0.4.0)

publicfinalclass SmoothGradConfigextendsGeneratedMessageV3implementsSmoothGradConfigOrBuilder

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.vertexai.v1.SmoothGradConfig

Inheritance

Object > AbstractMessageLite<MessageType,BuilderType> > AbstractMessage > GeneratedMessageV3 > SmoothGradConfig

Implements

SmoothGradConfigOrBuilder

Inherited Members

publicstaticfinalintFEATURE_NOISE_SIGMA_FIELD_NUMBER

publicstaticfinalintNOISE_SIGMA_FIELD_NUMBER

publicstaticfinalintNOISY_SAMPLE_COUNT_FIELD_NUMBER

publicstaticSmoothGradConfiggetDefaultInstance()

publicstaticfinalDescriptors.DescriptorgetDescriptor()

publicstaticSmoothGradConfig.BuildernewBuilder()

publicstaticSmoothGradConfig.BuildernewBuilder(SmoothGradConfigprototype)

publicstaticSmoothGradConfigparseDelimitedFrom(InputStreaminput)

publicstaticSmoothGradConfigparseDelimitedFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticSmoothGradConfigparseFrom(byte[]data)

publicstaticSmoothGradConfigparseFrom(byte[]data,ExtensionRegistryLiteextensionRegistry)

publicstaticSmoothGradConfigparseFrom(ByteStringdata)

publicstaticSmoothGradConfigparseFrom(ByteStringdata,ExtensionRegistryLiteextensionRegistry)

publicstaticSmoothGradConfigparseFrom(CodedInputStreaminput)

publicstaticSmoothGradConfigparseFrom(CodedInputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticSmoothGradConfigparseFrom(InputStreaminput)

publicstaticSmoothGradConfigparseFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticSmoothGradConfigparseFrom(ByteBufferdata)

publicstaticSmoothGradConfigparseFrom(ByteBufferdata,ExtensionRegistryLiteextensionRegistry)

publicstaticParser<SmoothGradConfig>parser()

publicbooleanequals(Objectobj)

AbstractMessage.equals(Object other)

publicSmoothGradConfiggetDefaultInstanceForType()

publicFeatureNoiseSigmagetFeatureNoiseSigma()

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.vertexai.v1.FeatureNoiseSigma feature_noise_sigma = 2;

publicFeatureNoiseSigmaOrBuildergetFeatureNoiseSigmaOrBuilder()

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.vertexai.v1.FeatureNoiseSigma feature_noise_sigma = 2;

publicSmoothGradConfig.GradientNoiseSigmaCasegetGradientNoiseSigmaCase()

publicfloatgetNoiseSigma()

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;

publicintgetNoisySampleCount()

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;

publicParser<SmoothGradConfig>getParserForType()

GeneratedMessageV3.getParserForType()

publicintgetSerializedSize()

GeneratedMessageV3.getSerializedSize()

publicbooleanhasFeatureNoiseSigma()

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.vertexai.v1.FeatureNoiseSigma feature_noise_sigma = 2;

publicbooleanhasNoiseSigma()

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;

publicinthashCode()

AbstractMessage.hashCode()

protectedGeneratedMessageV3.FieldAccessorTableinternalGetFieldAccessorTable()

GeneratedMessageV3.internalGetFieldAccessorTable()

publicfinalbooleanisInitialized()

GeneratedMessageV3.isInitialized()

publicSmoothGradConfig.BuildernewBuilderForType()

protectedSmoothGradConfig.BuildernewBuilderForType(GeneratedMessageV3.BuilderParentparent)

GeneratedMessageV3.newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protectedObjectnewInstance(GeneratedMessageV3.UnusedPrivateParameterunused)

GeneratedMessageV3.newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

publicSmoothGradConfig.BuildertoBuilder()

publicvoidwriteTo(CodedOutputStreamoutput)

GeneratedMessageV3.writeTo(CodedOutputStream output)