Class ExplanationParameters.Builder (1.2.0)

publicstaticfinalclass ExplanationParameters.BuilderextendsGeneratedMessageV3.Builder<ExplanationParameters.Builder>implementsExplanationParametersOrBuilder

Parameters to configure explaining for Model's predictions.

Protobuf type google.cloud.vertexai.v1.ExplanationParameters

Inheritance

Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessageV3.Builder > ExplanationParameters.Builder

Implements

ExplanationParametersOrBuilder

Inherited Members

publicstaticfinalDescriptors.DescriptorgetDescriptor()

publicExplanationParameters.BuilderaddRepeatedField(Descriptors.FieldDescriptorfield,Objectvalue)

GeneratedMessageV3.Builder<BuilderType>.addRepeatedField(Descriptors.FieldDescriptor field, Object value)

publicExplanationParametersbuild()

publicExplanationParametersbuildPartial()

publicExplanationParameters.Builderclear()

GeneratedMessageV3.Builder<BuilderType>.clear()

publicExplanationParameters.BuilderclearExamples()

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

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

publicExplanationParameters.BuilderclearField(Descriptors.FieldDescriptorfield)

GeneratedMessageV3.Builder<BuilderType>.clearField(Descriptors.FieldDescriptor field)

publicExplanationParameters.BuilderclearIntegratedGradientsAttribution()

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;

publicExplanationParameters.BuilderclearMethod()

publicExplanationParameters.BuilderclearOneof(Descriptors.OneofDescriptoroneof)

GeneratedMessageV3.Builder<BuilderType>.clearOneof(Descriptors.OneofDescriptor oneof)

publicExplanationParameters.BuilderclearOutputIndices()

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;

publicExplanationParameters.BuilderclearSampledShapleyAttribution()

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;

publicExplanationParameters.BuilderclearTopK()

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;

publicExplanationParameters.BuilderclearXraiAttribution()

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;

publicExplanationParameters.Builderclone()

GeneratedMessageV3.Builder<BuilderType>.clone()

publicExplanationParametersgetDefaultInstanceForType()

publicDescriptors.DescriptorgetDescriptorForType()

GeneratedMessageV3.Builder<BuilderType>.getDescriptorForType()

publicExamplesgetExamples()

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

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

publicExamples.BuildergetExamplesBuilder()

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

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

publicExamplesOrBuildergetExamplesOrBuilder()

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

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

publicIntegratedGradientsAttributiongetIntegratedGradientsAttribution()

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;

publicIntegratedGradientsAttribution.BuildergetIntegratedGradientsAttributionBuilder()

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;

publicIntegratedGradientsAttributionOrBuildergetIntegratedGradientsAttributionOrBuilder()

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;

publicExplanationParameters.MethodCasegetMethodCase()

publicListValuegetOutputIndices()

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;

publicListValue.BuildergetOutputIndicesBuilder()

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;

publicListValueOrBuildergetOutputIndicesOrBuilder()

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;

publicSampledShapleyAttributiongetSampledShapleyAttribution()

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;

publicSampledShapleyAttribution.BuildergetSampledShapleyAttributionBuilder()

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;

publicSampledShapleyAttributionOrBuildergetSampledShapleyAttributionOrBuilder()

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;

publicintgetTopK()

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;

publicXraiAttributiongetXraiAttribution()

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;

publicXraiAttribution.BuildergetXraiAttributionBuilder()

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;

publicXraiAttributionOrBuildergetXraiAttributionOrBuilder()

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;

publicbooleanhasExamples()

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

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

publicbooleanhasIntegratedGradientsAttribution()

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;

publicbooleanhasOutputIndices()

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;

publicbooleanhasSampledShapleyAttribution()

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;

publicbooleanhasXraiAttribution()

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;

protectedGeneratedMessageV3.FieldAccessorTableinternalGetFieldAccessorTable()

GeneratedMessageV3.Builder<BuilderType>.internalGetFieldAccessorTable()

publicfinalbooleanisInitialized()

GeneratedMessageV3.Builder<BuilderType>.isInitialized()

publicExplanationParameters.BuildermergeExamples(Examplesvalue)

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

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

publicExplanationParameters.BuildermergeFrom(ExplanationParametersother)

publicExplanationParameters.BuildermergeFrom(CodedInputStreaminput,ExtensionRegistryLiteextensionRegistry)

AbstractMessage.Builder<BuilderType>.mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

publicExplanationParameters.BuildermergeFrom(Messageother)

AbstractMessage.Builder<BuilderType>.mergeFrom(Message other)

publicExplanationParameters.BuildermergeIntegratedGradientsAttribution(IntegratedGradientsAttributionvalue)

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;

publicExplanationParameters.BuildermergeOutputIndices(ListValuevalue)

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;

publicExplanationParameters.BuildermergeSampledShapleyAttribution(SampledShapleyAttributionvalue)

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;

publicfinalExplanationParameters.BuildermergeUnknownFields(UnknownFieldSetunknownFields)

GeneratedMessageV3.Builder<BuilderType>.mergeUnknownFields(UnknownFieldSet unknownFields)

publicExplanationParameters.BuildermergeXraiAttribution(XraiAttributionvalue)

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;

publicExplanationParameters.BuildersetExamples(Examplesvalue)

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

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

publicExplanationParameters.BuildersetExamples(Examples.BuilderbuilderForValue)

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

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

publicExplanationParameters.BuildersetField(Descriptors.FieldDescriptorfield,Objectvalue)

GeneratedMessageV3.Builder<BuilderType>.setField(Descriptors.FieldDescriptor field, Object value)

publicExplanationParameters.BuildersetIntegratedGradientsAttribution(IntegratedGradientsAttributionvalue)

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;

publicExplanationParameters.BuildersetIntegratedGradientsAttribution(IntegratedGradientsAttribution.BuilderbuilderForValue)

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;

publicExplanationParameters.BuildersetOutputIndices(ListValuevalue)

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;

publicExplanationParameters.BuildersetOutputIndices(ListValue.BuilderbuilderForValue)

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;

publicExplanationParameters.BuildersetRepeatedField(Descriptors.FieldDescriptorfield,intindex,Objectvalue)

GeneratedMessageV3.Builder<BuilderType>.setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

publicExplanationParameters.BuildersetSampledShapleyAttribution(SampledShapleyAttributionvalue)

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;

publicExplanationParameters.BuildersetSampledShapleyAttribution(SampledShapleyAttribution.BuilderbuilderForValue)

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;

publicExplanationParameters.BuildersetTopK(intvalue)

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;

publicfinalExplanationParameters.BuildersetUnknownFields(UnknownFieldSetunknownFields)

GeneratedMessageV3.Builder<BuilderType>.setUnknownFields(UnknownFieldSet unknownFields)

publicExplanationParameters.BuildersetXraiAttribution(XraiAttributionvalue)

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;

publicExplanationParameters.BuildersetXraiAttribution(XraiAttribution.BuilderbuilderForValue)

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;