Class ExplanationParameters (2.9.8)

public final class ExplanationParameters extends GeneratedMessageV3 implements ExplanationParametersOrBuilder

Parameters to configure explaining for Model's predictions.

Protobuf type google.cloud.aiplatform.v1.ExplanationParameters

Static Fields

INTEGRATED_GRADIENTS_ATTRIBUTION_FIELD_NUMBER

public static final int INTEGRATED_GRADIENTS_ATTRIBUTION_FIELD_NUMBER
Field Value
TypeDescription
int

OUTPUT_INDICES_FIELD_NUMBER

public static final int OUTPUT_INDICES_FIELD_NUMBER
Field Value
TypeDescription
int

SAMPLED_SHAPLEY_ATTRIBUTION_FIELD_NUMBER

public static final int SAMPLED_SHAPLEY_ATTRIBUTION_FIELD_NUMBER
Field Value
TypeDescription
int

TOP_K_FIELD_NUMBER

public static final int TOP_K_FIELD_NUMBER
Field Value
TypeDescription
int

XRAI_ATTRIBUTION_FIELD_NUMBER

public static final int XRAI_ATTRIBUTION_FIELD_NUMBER
Field Value
TypeDescription
int

Static Methods

getDefaultInstance()

public static ExplanationParameters getDefaultInstance()
Returns
TypeDescription
ExplanationParameters

getDescriptor()

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

newBuilder()

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

newBuilder(ExplanationParameters prototype)

public static ExplanationParameters.Builder newBuilder(ExplanationParameters prototype)
Parameter
NameDescription
prototypeExplanationParameters
Returns
TypeDescription
ExplanationParameters.Builder

parseDelimitedFrom(InputStream input)

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

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

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

parseFrom(byte[] data)

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

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

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

parseFrom(ByteString data)

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

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

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

parseFrom(CodedInputStream input)

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

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

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

parseFrom(InputStream input)

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

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

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

parseFrom(ByteBuffer data)

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

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

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

parser()

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

Methods

equals(Object obj)

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

getDefaultInstanceForType()

public ExplanationParameters getDefaultInstanceForType()
Returns
TypeDescription
ExplanationParameters

getIntegratedGradientsAttribution()

public IntegratedGradientsAttribution getIntegratedGradientsAttribution()

An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

.google.cloud.aiplatform.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Returns
TypeDescription
IntegratedGradientsAttribution

The integratedGradientsAttribution.

getIntegratedGradientsAttributionOrBuilder()

public IntegratedGradientsAttributionOrBuilder getIntegratedGradientsAttributionOrBuilder()

An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

.google.cloud.aiplatform.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Returns
TypeDescription
IntegratedGradientsAttributionOrBuilder

getMethodCase()

public ExplanationParameters.MethodCase getMethodCase()
Returns
TypeDescription
ExplanationParameters.MethodCase

getOutputIndices()

public ListValue getOutputIndices()

If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indeices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).

.google.protobuf.ListValue output_indices = 5;

Returns
TypeDescription
ListValue

The outputIndices.

getOutputIndicesOrBuilder()

public ListValueOrBuilder getOutputIndicesOrBuilder()

If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indeices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).

.google.protobuf.ListValue output_indices = 5;

Returns
TypeDescription
ListValueOrBuilder

getParserForType()

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

getSampledShapleyAttribution()

public SampledShapleyAttribution getSampledShapleyAttribution()

An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.

.google.cloud.aiplatform.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Returns
TypeDescription
SampledShapleyAttribution

The sampledShapleyAttribution.

getSampledShapleyAttributionOrBuilder()

public SampledShapleyAttributionOrBuilder getSampledShapleyAttributionOrBuilder()

An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.

.google.cloud.aiplatform.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Returns
TypeDescription
SampledShapleyAttributionOrBuilder

getSerializedSize()

public int getSerializedSize()
Returns
TypeDescription
int
Overrides

getTopK()

public int getTopK()

If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.

int32 top_k = 4;

Returns
TypeDescription
int

The topK.

getUnknownFields()

public final UnknownFieldSet getUnknownFields()
Returns
TypeDescription
UnknownFieldSet
Overrides

getXraiAttribution()

public XraiAttribution getXraiAttribution()

An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.

.google.cloud.aiplatform.v1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
XraiAttribution

The xraiAttribution.

getXraiAttributionOrBuilder()

public XraiAttributionOrBuilder getXraiAttributionOrBuilder()

An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.

.google.cloud.aiplatform.v1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
XraiAttributionOrBuilder

hasIntegratedGradientsAttribution()

public boolean hasIntegratedGradientsAttribution()

An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

.google.cloud.aiplatform.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Returns
TypeDescription
boolean

Whether the integratedGradientsAttribution field is set.

hasOutputIndices()

public boolean hasOutputIndices()

If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indeices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).

.google.protobuf.ListValue output_indices = 5;

Returns
TypeDescription
boolean

Whether the outputIndices field is set.

hasSampledShapleyAttribution()

public boolean hasSampledShapleyAttribution()

An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.

.google.cloud.aiplatform.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Returns
TypeDescription
boolean

Whether the sampledShapleyAttribution field is set.

hasXraiAttribution()

public boolean hasXraiAttribution()

An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.

.google.cloud.aiplatform.v1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
boolean

Whether the xraiAttribution 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

newBuilderForType()

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

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

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

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

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

toBuilder()

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

writeTo(CodedOutputStream output)

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