Class ExplanationParameters.Builder (3.35.0)

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

Parameters to configure explaining for Model's predictions.

Protobuf type google.cloud.aiplatform.v1beta1.ExplanationParameters

Static Methods

getDescriptor()

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

Methods

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public ExplanationParameters.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

build()

public ExplanationParameters build()
Returns
TypeDescription
ExplanationParameters

buildPartial()

public ExplanationParameters buildPartial()
Returns
TypeDescription
ExplanationParameters

clear()

public ExplanationParameters.Builder clear()
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

clearExamples()

public ExplanationParameters.Builder clearExamples()

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Returns
TypeDescription
ExplanationParameters.Builder

clearField(Descriptors.FieldDescriptor field)

public ExplanationParameters.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
NameDescription
fieldFieldDescriptor
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

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.aiplatform.v1beta1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Returns
TypeDescription
ExplanationParameters.Builder

clearMethod()

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

clearOneof(Descriptors.OneofDescriptor oneof)

public ExplanationParameters.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
NameDescription
oneofOneofDescriptor
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

clearOutputIndices()

public ExplanationParameters.Builder clearOutputIndices()

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_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;

Returns
TypeDescription
ExplanationParameters.Builder

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.aiplatform.v1beta1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Returns
TypeDescription
ExplanationParameters.Builder

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
TypeDescription
ExplanationParameters.Builder

This builder for chaining.

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.aiplatform.v1beta1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
ExplanationParameters.Builder

clone()

public ExplanationParameters.Builder clone()
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

getDefaultInstanceForType()

public ExplanationParameters getDefaultInstanceForType()
Returns
TypeDescription
ExplanationParameters

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
TypeDescription
Descriptor
Overrides

getExamples()

public Examples getExamples()

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Returns
TypeDescription
Examples

The examples.

getExamplesBuilder()

public Examples.Builder getExamplesBuilder()

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Returns
TypeDescription
Examples.Builder

getExamplesOrBuilder()

public ExamplesOrBuilder getExamplesOrBuilder()

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Returns
TypeDescription
ExamplesOrBuilder

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.v1beta1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Returns
TypeDescription
IntegratedGradientsAttribution

The integratedGradientsAttribution.

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.aiplatform.v1beta1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Returns
TypeDescription
IntegratedGradientsAttribution.Builder

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.v1beta1.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_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;

Returns
TypeDescription
ListValue

The outputIndices.

getOutputIndicesBuilder()

public ListValue.Builder getOutputIndicesBuilder()

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_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;

Returns
TypeDescription
Builder

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_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;

Returns
TypeDescription
ListValueOrBuilder

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.v1beta1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Returns
TypeDescription
SampledShapleyAttribution

The sampledShapleyAttribution.

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.aiplatform.v1beta1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Returns
TypeDescription
SampledShapleyAttribution.Builder

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.v1beta1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Returns
TypeDescription
SampledShapleyAttributionOrBuilder

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.

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.v1beta1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
XraiAttribution

The xraiAttribution.

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.aiplatform.v1beta1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
XraiAttribution.Builder

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.v1beta1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
XraiAttributionOrBuilder

hasExamples()

public boolean hasExamples()

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Returns
TypeDescription
boolean

Whether the examples field is set.

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.v1beta1.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_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;

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.v1beta1.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.v1beta1.XraiAttribution xrai_attribution = 3;

Returns
TypeDescription
boolean

Whether the xraiAttribution field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

mergeExamples(Examples value)

public ExplanationParameters.Builder mergeExamples(Examples value)

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Parameter
NameDescription
valueExamples
Returns
TypeDescription
ExplanationParameters.Builder

mergeFrom(ExplanationParameters other)

public ExplanationParameters.Builder mergeFrom(ExplanationParameters other)
Parameter
NameDescription
otherExplanationParameters
Returns
TypeDescription
ExplanationParameters.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public ExplanationParameters.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
ExplanationParameters.Builder
Overrides
Exceptions
TypeDescription
IOException

mergeFrom(Message other)

public ExplanationParameters.Builder mergeFrom(Message other)
Parameter
NameDescription
otherMessage
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

mergeIntegratedGradientsAttribution(IntegratedGradientsAttribution value)

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.aiplatform.v1beta1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Parameter
NameDescription
valueIntegratedGradientsAttribution
Returns
TypeDescription
ExplanationParameters.Builder

mergeOutputIndices(ListValue value)

public ExplanationParameters.Builder mergeOutputIndices(ListValue value)

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_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;

Parameter
NameDescription
valueListValue
Returns
TypeDescription
ExplanationParameters.Builder

mergeSampledShapleyAttribution(SampledShapleyAttribution value)

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.aiplatform.v1beta1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Parameter
NameDescription
valueSampledShapleyAttribution
Returns
TypeDescription
ExplanationParameters.Builder

mergeUnknownFields(UnknownFieldSet unknownFields)

public final ExplanationParameters.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

mergeXraiAttribution(XraiAttribution value)

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.aiplatform.v1beta1.XraiAttribution xrai_attribution = 3;

Parameter
NameDescription
valueXraiAttribution
Returns
TypeDescription
ExplanationParameters.Builder

setExamples(Examples value)

public ExplanationParameters.Builder setExamples(Examples value)

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Parameter
NameDescription
valueExamples
Returns
TypeDescription
ExplanationParameters.Builder

setExamples(Examples.Builder builderForValue)

public ExplanationParameters.Builder setExamples(Examples.Builder builderForValue)

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

.google.cloud.aiplatform.v1beta1.Examples examples = 7;

Parameter
NameDescription
builderForValueExamples.Builder
Returns
TypeDescription
ExplanationParameters.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public ExplanationParameters.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

setIntegratedGradientsAttribution(IntegratedGradientsAttribution value)

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.aiplatform.v1beta1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Parameter
NameDescription
valueIntegratedGradientsAttribution
Returns
TypeDescription
ExplanationParameters.Builder

setIntegratedGradientsAttribution(IntegratedGradientsAttribution.Builder builderForValue)

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.aiplatform.v1beta1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;

Parameter
NameDescription
builderForValueIntegratedGradientsAttribution.Builder
Returns
TypeDescription
ExplanationParameters.Builder

setOutputIndices(ListValue value)

public ExplanationParameters.Builder setOutputIndices(ListValue value)

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_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;

Parameter
NameDescription
valueListValue
Returns
TypeDescription
ExplanationParameters.Builder

setOutputIndices(ListValue.Builder builderForValue)

public ExplanationParameters.Builder setOutputIndices(ListValue.Builder builderForValue)

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_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;

Parameter
NameDescription
builderForValueBuilder
Returns
TypeDescription
ExplanationParameters.Builder

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public ExplanationParameters.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
NameDescription
fieldFieldDescriptor
indexint
valueObject
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

setSampledShapleyAttribution(SampledShapleyAttribution value)

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.aiplatform.v1beta1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Parameter
NameDescription
valueSampledShapleyAttribution
Returns
TypeDescription
ExplanationParameters.Builder

setSampledShapleyAttribution(SampledShapleyAttribution.Builder builderForValue)

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.aiplatform.v1beta1.SampledShapleyAttribution sampled_shapley_attribution = 1;

Parameter
NameDescription
builderForValueSampledShapleyAttribution.Builder
Returns
TypeDescription
ExplanationParameters.Builder

setTopK(int value)

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;

Parameter
NameDescription
valueint

The topK to set.

Returns
TypeDescription
ExplanationParameters.Builder

This builder for chaining.

setUnknownFields(UnknownFieldSet unknownFields)

public final ExplanationParameters.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ExplanationParameters.Builder
Overrides

setXraiAttribution(XraiAttribution value)

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.aiplatform.v1beta1.XraiAttribution xrai_attribution = 3;

Parameter
NameDescription
valueXraiAttribution
Returns
TypeDescription
ExplanationParameters.Builder

setXraiAttribution(XraiAttribution.Builder builderForValue)

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.aiplatform.v1beta1.XraiAttribution xrai_attribution = 3;

Parameter
NameDescription
builderForValueXraiAttribution.Builder
Returns
TypeDescription
ExplanationParameters.Builder