Package com.google.cloud.aiplatform.v1

Class ExplanationParameters

  • All Implemented Interfaces:
    ExplanationParametersOrBuilder, com.google.protobuf.Message, com.google.protobuf.MessageLite, com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder, Serializable
    public final class ExplanationParameters
extends com.google.protobuf.GeneratedMessageV3
implements ExplanationParametersOrBuilder
     Parameters to configure explaining for Model's predictions.
    Protobuf type google.cloud.aiplatform.v1.ExplanationParameters
    See Also:
    Serialized Form

    • Field Detail

      • SAMPLED_SHAPLEY_ATTRIBUTION_FIELD_NUMBER

        public static final int SAMPLED_SHAPLEY_ATTRIBUTION_FIELD_NUMBER
        See Also:
        Constant Field Values

      • INTEGRATED_GRADIENTS_ATTRIBUTION_FIELD_NUMBER

        public static final int INTEGRATED_GRADIENTS_ATTRIBUTION_FIELD_NUMBER
        See Also:
        Constant Field Values

      • XRAI_ATTRIBUTION_FIELD_NUMBER

        public static final int XRAI_ATTRIBUTION_FIELD_NUMBER
        See Also:
        Constant Field Values

      • OUTPUT_INDICES_FIELD_NUMBER

        public static final int OUTPUT_INDICES_FIELD_NUMBER
        See Also:
        Constant Field Values

    • Method Detail

      • newInstance

        protected Object newInstance​(com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter unused)
        Overrides:
        newInstance in class com.google.protobuf.GeneratedMessageV3

      • 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

      • 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;
        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.aiplatform.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;
        Specified by:
        getSampledShapleyAttribution in interface ExplanationParametersOrBuilder
        Returns:
        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;
        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.aiplatform.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.aiplatform.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;
        Specified by:
        getIntegratedGradientsAttribution in interface ExplanationParametersOrBuilder
        Returns:
        The integratedGradientsAttribution.

      • 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;
        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.aiplatform.v1.XraiAttribution xrai_attribution = 3;
        Specified by:
        getXraiAttribution in interface ExplanationParametersOrBuilder
        Returns:
        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;
        Specified by:
        getXraiAttributionOrBuilder in interface ExplanationParametersOrBuilder

      • hasExamples

        public boolean hasExamples()
         Example-based explanations that returns the nearest neighbors from the
 provided dataset.
        .google.cloud.aiplatform.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.aiplatform.v1.Examples examples = 7;
        Specified by:
        getExamples in interface ExplanationParametersOrBuilder
        Returns:
        The examples.

      • 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.

      • 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.

      • 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

      • isInitialized

        public final boolean isInitialized()
        Specified by:
        isInitialized in interface com.google.protobuf.MessageLiteOrBuilder
        Overrides:
        isInitialized in class com.google.protobuf.GeneratedMessageV3

      • writeTo

        public void writeTo​(com.google.protobuf.CodedOutputStream output)
             throws IOException
        Specified by:
        writeTo in interface com.google.protobuf.MessageLite
        Overrides:
        writeTo in class com.google.protobuf.GeneratedMessageV3
        Throws:
        IOException

      • getSerializedSize

        public int getSerializedSize()
        Specified by:
        getSerializedSize in interface com.google.protobuf.MessageLite
        Overrides:
        getSerializedSize in class com.google.protobuf.GeneratedMessageV3

      • equals

        public boolean equals​(Object obj)
        Specified by:
        equals in interface com.google.protobuf.Message
        Overrides:
        equals in class com.google.protobuf.AbstractMessage

      • hashCode

        public int hashCode()
        Specified by:
        hashCode in interface com.google.protobuf.Message
        Overrides:
        hashCode in class com.google.protobuf.AbstractMessage

      • parseFrom

        public static ExplanationParameters parseFrom​(ByteBuffer data)
                                       throws com.google.protobuf.InvalidProtocolBufferException
        Throws:
        com.google.protobuf.InvalidProtocolBufferException

      • parseFrom

        public static ExplanationParameters parseFrom​(ByteBuffer data,
                                              com.google.protobuf.ExtensionRegistryLite extensionRegistry)
                                       throws com.google.protobuf.InvalidProtocolBufferException
        Throws:
        com.google.protobuf.InvalidProtocolBufferException

      • parseFrom

        public static ExplanationParameters parseFrom​(com.google.protobuf.ByteString data)
                                       throws com.google.protobuf.InvalidProtocolBufferException
        Throws:
        com.google.protobuf.InvalidProtocolBufferException

      • parseFrom

        public static ExplanationParameters parseFrom​(com.google.protobuf.ByteString data,
                                              com.google.protobuf.ExtensionRegistryLite extensionRegistry)
                                       throws com.google.protobuf.InvalidProtocolBufferException
        Throws:
        com.google.protobuf.InvalidProtocolBufferException

      • parseFrom

        public static ExplanationParameters parseFrom​(byte[] data)
                                       throws com.google.protobuf.InvalidProtocolBufferException
        Throws:
        com.google.protobuf.InvalidProtocolBufferException

      • parseFrom

        public static ExplanationParameters parseFrom​(byte[] data,
                                              com.google.protobuf.ExtensionRegistryLite extensionRegistry)
                                       throws com.google.protobuf.InvalidProtocolBufferException
        Throws:
        com.google.protobuf.InvalidProtocolBufferException

      • newBuilderForType

        public ExplanationParameters.Builder newBuilderForType()
        Specified by:
        newBuilderForType in interface com.google.protobuf.Message
        Specified by:
        newBuilderForType in interface com.google.protobuf.MessageLite

      • toBuilder

        public ExplanationParameters.Builder toBuilder()
        Specified by:
        toBuilder in interface com.google.protobuf.Message
        Specified by:
        toBuilder in interface com.google.protobuf.MessageLite

      • newBuilderForType

        protected ExplanationParameters.Builder newBuilderForType​(com.google.protobuf.GeneratedMessageV3.BuilderParent parent)
        Specified by:
        newBuilderForType in class com.google.protobuf.GeneratedMessageV3

      • getParserForType

        public com.google.protobuf.Parser<ExplanationParameters> getParserForType()
        Specified by:
        getParserForType in interface com.google.protobuf.Message
        Specified by:
        getParserForType in interface com.google.protobuf.MessageLite
        Overrides:
        getParserForType in class com.google.protobuf.GeneratedMessageV3

      • getDefaultInstanceForType

        public ExplanationParameters getDefaultInstanceForType()
        Specified by:
        getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuilder
        Specified by:
        getDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilder