com.google.cloud.vertexai.api

Class ExplanationParameters.Builder

java.lang.Object

com.google.protobuf.AbstractMessageLite.Builder

com.google.protobuf.AbstractMessage.Builder<BuilderT>

com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

com.google.cloud.vertexai.api.ExplanationParameters.Builder

All Implemented Interfaces:

ExplanationParametersOrBuilder, com.google.protobuf.Message.Builder, com.google.protobuf.MessageLite.Builder, com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder, Cloneable

Enclosing class:

ExplanationParameters

public static final class ExplanationParameters.Builder
extends com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>
implements ExplanationParametersOrBuilder

 Parameters to configure explaining for Model's predictions.
 

Protobuf type google.cloud.vertexai.v1.ExplanationParameters

Method Summary

Modifier and Type	Method and Description
ExplanationParameters.Builder	addRepeatedField(com.google.protobuf.Descriptors.FieldDescriptor field, Object value)
ExplanationParameters	build()
ExplanationParameters	buildPartial()
ExplanationParameters.Builder	clear()
ExplanationParameters.Builder	clearExamples() Example-based explanations that returns the nearest neighbors from the provided dataset.
ExplanationParameters.Builder	clearField(com.google.protobuf.Descriptors.FieldDescriptor field)
ExplanationParameters.Builder	clearIntegratedGradientsAttribution() An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
ExplanationParameters.Builder	clearMethod()
ExplanationParameters.Builder	clearOneof(com.google.protobuf.Descriptors.OneofDescriptor oneof)
ExplanationParameters.Builder	clearOutputIndices() If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
ExplanationParameters.Builder	clearSampledShapleyAttribution() An attribution method that approximates Shapley values for features that contribute to the label being predicted.
ExplanationParameters.Builder	clearTopK() If populated, returns attributions for top K indices of outputs (defaults to 1).
ExplanationParameters.Builder	clearXraiAttribution() An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.
ExplanationParameters.Builder	clone()
ExplanationParameters	getDefaultInstanceForType()
static com.google.protobuf.Descriptors.Descriptor	getDescriptor()
com.google.protobuf.Descriptors.Descriptor	getDescriptorForType()
Examples	getExamples() Example-based explanations that returns the nearest neighbors from the provided dataset.
Examples.Builder	getExamplesBuilder() Example-based explanations that returns the nearest neighbors from the provided dataset.
ExamplesOrBuilder	getExamplesOrBuilder() Example-based explanations that returns the nearest neighbors from the provided dataset.
IntegratedGradientsAttribution	getIntegratedGradientsAttribution() An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
IntegratedGradientsAttribution.Builder	getIntegratedGradientsAttributionBuilder() An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
IntegratedGradientsAttributionOrBuilder	getIntegratedGradientsAttributionOrBuilder() An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
ExplanationParameters.MethodCase	getMethodCase()
com.google.protobuf.ListValue	getOutputIndices() If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
com.google.protobuf.ListValue.Builder	getOutputIndicesBuilder() If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
com.google.protobuf.ListValueOrBuilder	getOutputIndicesOrBuilder() If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
SampledShapleyAttribution	getSampledShapleyAttribution() An attribution method that approximates Shapley values for features that contribute to the label being predicted.
SampledShapleyAttribution.Builder	getSampledShapleyAttributionBuilder() An attribution method that approximates Shapley values for features that contribute to the label being predicted.
SampledShapleyAttributionOrBuilder	getSampledShapleyAttributionOrBuilder() An attribution method that approximates Shapley values for features that contribute to the label being predicted.
int	getTopK() If populated, returns attributions for top K indices of outputs (defaults to 1).
XraiAttribution	getXraiAttribution() An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.
XraiAttribution.Builder	getXraiAttributionBuilder() An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.
XraiAttributionOrBuilder	getXraiAttributionOrBuilder() An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.
boolean	hasExamples() Example-based explanations that returns the nearest neighbors from the provided dataset.
boolean	hasIntegratedGradientsAttribution() An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
boolean	hasOutputIndices() If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
boolean	hasSampledShapleyAttribution() An attribution method that approximates Shapley values for features that contribute to the label being predicted.
boolean	hasXraiAttribution() An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.
protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable	internalGetFieldAccessorTable()
boolean	isInitialized()
ExplanationParameters.Builder	mergeExamples(Examples value) Example-based explanations that returns the nearest neighbors from the provided dataset.
ExplanationParameters.Builder	mergeFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
ExplanationParameters.Builder	mergeFrom(ExplanationParameters other)
ExplanationParameters.Builder	mergeFrom(com.google.protobuf.Message other)
ExplanationParameters.Builder	mergeIntegratedGradientsAttribution(IntegratedGradientsAttribution value) An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
ExplanationParameters.Builder	mergeOutputIndices(com.google.protobuf.ListValue value) If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
ExplanationParameters.Builder	mergeSampledShapleyAttribution(SampledShapleyAttribution value) An attribution method that approximates Shapley values for features that contribute to the label being predicted.
ExplanationParameters.Builder	mergeUnknownFields(com.google.protobuf.UnknownFieldSet unknownFields)
ExplanationParameters.Builder	mergeXraiAttribution(XraiAttribution value) An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.
ExplanationParameters.Builder	setExamples(Examples.Builder builderForValue) Example-based explanations that returns the nearest neighbors from the provided dataset.
ExplanationParameters.Builder	setExamples(Examples value) Example-based explanations that returns the nearest neighbors from the provided dataset.
ExplanationParameters.Builder	setField(com.google.protobuf.Descriptors.FieldDescriptor field, Object value)
ExplanationParameters.Builder	setIntegratedGradientsAttribution(IntegratedGradientsAttribution.Builder builderForValue) An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
ExplanationParameters.Builder	setIntegratedGradientsAttribution(IntegratedGradientsAttribution value) An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure.
ExplanationParameters.Builder	setOutputIndices(com.google.protobuf.ListValue.Builder builderForValue) If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
ExplanationParameters.Builder	setOutputIndices(com.google.protobuf.ListValue value) If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1.Attribution.output_index] contained in output_indices.
ExplanationParameters.Builder	setRepeatedField(com.google.protobuf.Descriptors.FieldDescriptor field, int index, Object value)
ExplanationParameters.Builder	setSampledShapleyAttribution(SampledShapleyAttribution.Builder builderForValue) An attribution method that approximates Shapley values for features that contribute to the label being predicted.
ExplanationParameters.Builder	setSampledShapleyAttribution(SampledShapleyAttribution value) An attribution method that approximates Shapley values for features that contribute to the label being predicted.
ExplanationParameters.Builder	setTopK(int value) If populated, returns attributions for top K indices of outputs (defaults to 1).
ExplanationParameters.Builder	setUnknownFields(com.google.protobuf.UnknownFieldSet unknownFields)
ExplanationParameters.Builder	setXraiAttribution(XraiAttribution.Builder builderForValue) An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.
ExplanationParameters.Builder	setXraiAttribution(XraiAttribution value) An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure.

Methods inherited from class com.google.protobuf.GeneratedMessageV3.Builder

getAllFields, getField, getFieldBuilder, getOneofFieldDescriptor, getParentForChildren, getRepeatedField, getRepeatedFieldBuilder, getRepeatedFieldCount, getUnknownFields, getUnknownFieldSetBuilder, hasField, hasOneof, internalGetMapField, internalGetMapFieldReflection, internalGetMutableMapField, internalGetMutableMapFieldReflection, isClean, markClean, mergeUnknownLengthDelimitedField, mergeUnknownVarintField, newBuilderForField, onBuilt, onChanged, parseUnknownField, setUnknownFieldSetBuilder, setUnknownFieldsProto3

Methods inherited from class com.google.protobuf.AbstractMessage.Builder

findInitializationErrors, getInitializationErrorString, internalMergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, newUninitializedMessageException, toString

Methods inherited from class com.google.protobuf.AbstractMessageLite.Builder

addAll, addAll, mergeDelimitedFrom, mergeDelimitedFrom, newUninitializedMessageException

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface com.google.protobuf.MessageOrBuilder

findInitializationErrors, getAllFields, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof

Methods inherited from interface com.google.protobuf.Message.Builder

mergeDelimitedFrom, mergeDelimitedFrom

Method Detail

getDescriptor

public static final com.google.protobuf.Descriptors.Descriptor getDescriptor()

internalGetFieldAccessorTable

protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()

Specified by:

internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

clear

public ExplanationParameters.Builder clear()

Specified by:

clear in interface com.google.protobuf.Message.Builder

Specified by:

clear in interface com.google.protobuf.MessageLite.Builder

Overrides:

clear in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

getDescriptorForType

public com.google.protobuf.Descriptors.Descriptor getDescriptorForType()

Specified by:

getDescriptorForType in interface com.google.protobuf.Message.Builder

Specified by:

getDescriptorForType in interface com.google.protobuf.MessageOrBuilder

Overrides:

getDescriptorForType in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

getDefaultInstanceForType

public ExplanationParameters getDefaultInstanceForType()

Specified by:

getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuilder

Specified by:

getDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilder

build

public ExplanationParameters build()

Specified by:

build in interface com.google.protobuf.Message.Builder

Specified by:

build in interface com.google.protobuf.MessageLite.Builder

buildPartial

public ExplanationParameters buildPartial()

Specified by:

buildPartial in interface com.google.protobuf.Message.Builder

Specified by:

buildPartial in interface com.google.protobuf.MessageLite.Builder

clone

public ExplanationParameters.Builder clone()

Specified by:

clone in interface com.google.protobuf.Message.Builder

Specified by:

clone in interface com.google.protobuf.MessageLite.Builder

Overrides:

clone in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

setField

public ExplanationParameters.Builder setField(com.google.protobuf.Descriptors.FieldDescriptor field,
                                              Object value)

Specified by:

setField in interface com.google.protobuf.Message.Builder

Overrides:

setField in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

clearField

public ExplanationParameters.Builder clearField(com.google.protobuf.Descriptors.FieldDescriptor field)

Specified by:

clearField in interface com.google.protobuf.Message.Builder

Overrides:

clearField in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

clearOneof

public ExplanationParameters.Builder clearOneof(com.google.protobuf.Descriptors.OneofDescriptor oneof)

Specified by:

clearOneof in interface com.google.protobuf.Message.Builder

Overrides:

clearOneof in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

setRepeatedField

public ExplanationParameters.Builder setRepeatedField(com.google.protobuf.Descriptors.FieldDescriptor field,
                                                      int index,
                                                      Object value)

Specified by:

setRepeatedField in interface com.google.protobuf.Message.Builder

Overrides:

setRepeatedField in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

addRepeatedField

public ExplanationParameters.Builder addRepeatedField(com.google.protobuf.Descriptors.FieldDescriptor field,
                                                      Object value)

Specified by:

addRepeatedField in interface com.google.protobuf.Message.Builder

Overrides:

addRepeatedField in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

mergeFrom

public ExplanationParameters.Builder mergeFrom(com.google.protobuf.Message other)

Specified by:

mergeFrom in interface com.google.protobuf.Message.Builder

Overrides:

mergeFrom in class com.google.protobuf.AbstractMessage.Builder<ExplanationParameters.Builder>

mergeFrom

public ExplanationParameters.Builder mergeFrom(ExplanationParameters other)

isInitialized

public final boolean isInitialized()

Specified by:

isInitialized in interface com.google.protobuf.MessageLiteOrBuilder

Overrides:

isInitialized in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

mergeFrom

public ExplanationParameters.Builder mergeFrom(com.google.protobuf.CodedInputStream input,
                                               com.google.protobuf.ExtensionRegistryLite extensionRegistry)
                                        throws IOException

Specified by:

mergeFrom in interface com.google.protobuf.Message.Builder

Specified by:

mergeFrom in interface com.google.protobuf.MessageLite.Builder

Overrides:

mergeFrom in class com.google.protobuf.AbstractMessage.Builder<ExplanationParameters.Builder>

Throws:

IOException

getMethodCase

public ExplanationParameters.MethodCase getMethodCase()

Specified by:

getMethodCase in interface ExplanationParametersOrBuilder

clearMethod

public ExplanationParameters.Builder clearMethod()

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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Specified by:

hasSampledShapleyAttribution in interface ExplanationParametersOrBuilder

Returns:

Whether the sampledShapleyAttribution field is set.

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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Specified by:

getSampledShapleyAttribution in interface ExplanationParametersOrBuilder

Returns:

The sampledShapleyAttribution.

setSampledShapleyAttribution

public ExplanationParameters.Builder setSampledShapleyAttribution(SampledShapleyAttribution value)

 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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

setSampledShapleyAttribution

public ExplanationParameters.Builder setSampledShapleyAttribution(SampledShapleyAttribution.Builder builderForValue)

 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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

mergeSampledShapleyAttribution

public ExplanationParameters.Builder mergeSampledShapleyAttribution(SampledShapleyAttribution value)

 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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

clearSampledShapleyAttribution

public ExplanationParameters.Builder clearSampledShapleyAttribution()

 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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

getSampledShapleyAttributionBuilder

public SampledShapleyAttribution.Builder getSampledShapleyAttributionBuilder()

 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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

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.vertexai.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Specified by:

getSampledShapleyAttributionOrBuilder in interface ExplanationParametersOrBuilder

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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Specified by:

hasIntegratedGradientsAttribution in interface ExplanationParametersOrBuilder

Returns:

Whether the integratedGradientsAttribution field is set.

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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Specified by:

getIntegratedGradientsAttribution in interface ExplanationParametersOrBuilder

Returns:

The integratedGradientsAttribution.

setIntegratedGradientsAttribution

public ExplanationParameters.Builder setIntegratedGradientsAttribution(IntegratedGradientsAttribution value)

 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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

setIntegratedGradientsAttribution

public ExplanationParameters.Builder setIntegratedGradientsAttribution(IntegratedGradientsAttribution.Builder builderForValue)

 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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

mergeIntegratedGradientsAttribution

public ExplanationParameters.Builder mergeIntegratedGradientsAttribution(IntegratedGradientsAttribution value)

 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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

clearIntegratedGradientsAttribution

public ExplanationParameters.Builder clearIntegratedGradientsAttribution()

 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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

getIntegratedGradientsAttributionBuilder

public IntegratedGradientsAttribution.Builder getIntegratedGradientsAttributionBuilder()

 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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

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.vertexai.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Specified by:

getIntegratedGradientsAttributionOrBuilder in interface ExplanationParametersOrBuilder

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.vertexai.v1.XraiAttribution xrai_attribution = 3;

Specified by:

hasXraiAttribution in interface ExplanationParametersOrBuilder

Returns:

Whether the xraiAttribution field is set.

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.vertexai.v1.XraiAttribution xrai_attribution = 3;

Specified by:

getXraiAttribution in interface ExplanationParametersOrBuilder

Returns:

The xraiAttribution.

setXraiAttribution

public ExplanationParameters.Builder setXraiAttribution(XraiAttribution value)

 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.vertexai.v1.XraiAttribution xrai_attribution = 3;

setXraiAttribution

public ExplanationParameters.Builder setXraiAttribution(XraiAttribution.Builder builderForValue)

 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.vertexai.v1.XraiAttribution xrai_attribution = 3;

mergeXraiAttribution

public ExplanationParameters.Builder mergeXraiAttribution(XraiAttribution value)

 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.vertexai.v1.XraiAttribution xrai_attribution = 3;

clearXraiAttribution

public ExplanationParameters.Builder clearXraiAttribution()

 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.vertexai.v1.XraiAttribution xrai_attribution = 3;

getXraiAttributionBuilder

public XraiAttribution.Builder getXraiAttributionBuilder()

 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.vertexai.v1.XraiAttribution xrai_attribution = 3;

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.vertexai.v1.XraiAttribution xrai_attribution = 3;

Specified by:

getXraiAttributionOrBuilder in interface ExplanationParametersOrBuilder

hasExamples

public boolean hasExamples()

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

Specified by:

hasExamples in interface ExplanationParametersOrBuilder

Returns:

Whether the examples field is set.

getExamples

public Examples getExamples()

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

Specified by:

getExamples in interface ExplanationParametersOrBuilder

Returns:

The examples.

setExamples

public ExplanationParameters.Builder setExamples(Examples value)

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

setExamples

public ExplanationParameters.Builder setExamples(Examples.Builder builderForValue)

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

mergeExamples

public ExplanationParameters.Builder mergeExamples(Examples value)

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

clearExamples

public ExplanationParameters.Builder clearExamples()

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

getExamplesBuilder

public Examples.Builder getExamplesBuilder()

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

getExamplesOrBuilder

public ExamplesOrBuilder getExamplesOrBuilder()

 Example-based explanations that returns the nearest neighbors from the
 provided dataset.
 

.google.cloud.vertexai.v1.Examples examples = 7;

Specified by:

getExamplesOrBuilder in interface ExplanationParametersOrBuilder

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;

Specified by:

getTopK in interface ExplanationParametersOrBuilder

Returns:

The topK.

setTopK

public ExplanationParameters.Builder setTopK(int value)

 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;

Parameters:

value - The topK to set.

Returns:

This builder for chaining.

clearTopK

public ExplanationParameters.Builder clearTopK()

 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:

This builder for chaining.

hasOutputIndices

public boolean hasOutputIndices()

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

Specified by:

hasOutputIndices in interface ExplanationParametersOrBuilder

Returns:

Whether the outputIndices field is set.

getOutputIndices

public com.google.protobuf.ListValue getOutputIndices()

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

Specified by:

getOutputIndices in interface ExplanationParametersOrBuilder

Returns:

The outputIndices.

setOutputIndices

public ExplanationParameters.Builder setOutputIndices(com.google.protobuf.ListValue value)

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

setOutputIndices

public ExplanationParameters.Builder setOutputIndices(com.google.protobuf.ListValue.Builder builderForValue)

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

mergeOutputIndices

public ExplanationParameters.Builder mergeOutputIndices(com.google.protobuf.ListValue value)

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

clearOutputIndices

public ExplanationParameters.Builder clearOutputIndices()

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

getOutputIndicesBuilder

public com.google.protobuf.ListValue.Builder getOutputIndicesBuilder()

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

getOutputIndicesOrBuilder

public com.google.protobuf.ListValueOrBuilder getOutputIndicesOrBuilder()

 If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1.Attribution.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][google.cloud.aiplatform.v1.ExplanationParameters.top_k] indices of
 outputs. If neither top_k nor output_indices 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;

Specified by:

getOutputIndicesOrBuilder in interface ExplanationParametersOrBuilder

setUnknownFields

public final ExplanationParameters.Builder setUnknownFields(com.google.protobuf.UnknownFieldSet unknownFields)

Specified by:

setUnknownFields in interface com.google.protobuf.Message.Builder

Overrides:

setUnknownFields in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>

mergeUnknownFields

public final ExplanationParameters.Builder mergeUnknownFields(com.google.protobuf.UnknownFieldSet unknownFields)

Specified by:

mergeUnknownFields in interface com.google.protobuf.Message.Builder

Overrides:

mergeUnknownFields in class com.google.protobuf.GeneratedMessageV3.Builder<ExplanationParameters.Builder>