Package com.google.cloud.aiplatform.v1beta1

Interface ExplanationParametersOrBuilder

  • All Superinterfaces:
    com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
    All Known Implementing Classes:
    ExplanationParameters, ExplanationParameters.Builder
    public interface ExplanationParametersOrBuilder
extends com.google.protobuf.MessageOrBuilder

    • Method Summary

      All Methods Instance Methods Abstract Methods 
      Modifier and Type Method Description
      Examples getExamples()
      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.
      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.v1beta1.Attribution.output_index] contained in output_indices.
      com.google.protobuf.ListValueOrBuilder getOutputIndicesOrBuilder()
      If populated, only returns attributions that have [output_index][google.cloud.aiplatform.v1beta1.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.
      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.
      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.v1beta1.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.

      • Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

        isInitialized

      • Methods inherited from interface com.google.protobuf.MessageOrBuilder

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

    • Method Detail

      • hasSampledShapleyAttribution

        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:
        Whether the sampledShapleyAttribution field is set.

      • getSampledShapleyAttribution

        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:
        The sampledShapleyAttribution.

      • getSampledShapleyAttributionOrBuilder

        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;

      • hasIntegratedGradientsAttribution

        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:
        Whether the integratedGradientsAttribution field is set.

      • getIntegratedGradientsAttribution

        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:
        The integratedGradientsAttribution.

      • getIntegratedGradientsAttributionOrBuilder

        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;

      • hasXraiAttribution

        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:
        Whether the xraiAttribution field is set.

      • getXraiAttribution

        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:
        The xraiAttribution.

      • getXraiAttributionOrBuilder

        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;

      • hasExamples

        boolean hasExamples()
         Example-based explanations that returns the nearest neighbors from the
 provided dataset.
        .google.cloud.aiplatform.v1beta1.Examples examples = 7;
        Returns:
        Whether the examples field is set.

      • getExamples

        Examples getExamples()
         Example-based explanations that returns the nearest neighbors from the
 provided dataset.
        .google.cloud.aiplatform.v1beta1.Examples examples = 7;
        Returns:
        The examples.

      • getExamplesOrBuilder

        ExamplesOrBuilder getExamplesOrBuilder()
         Example-based explanations that returns the nearest neighbors from the
 provided dataset.
        .google.cloud.aiplatform.v1beta1.Examples examples = 7;

      • getTopK

        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:
        The topK.

      • hasOutputIndices

        boolean hasOutputIndices()
         If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1beta1.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.v1beta1.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;
        Returns:
        Whether the outputIndices field is set.

      • getOutputIndices

        com.google.protobuf.ListValue getOutputIndices()
         If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1beta1.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.v1beta1.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;
        Returns:
        The outputIndices.

      • getOutputIndicesOrBuilder

        com.google.protobuf.ListValueOrBuilder getOutputIndicesOrBuilder()
         If populated, only returns attributions that have
 [output_index][google.cloud.aiplatform.v1beta1.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.v1beta1.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;