public final class ExplanationParameters extends GeneratedMessageV3 implements ExplanationParametersOrBuilder
Parameters to configure explaining for Model's predictions.
Protobuf type google.cloud.aiplatform.v1beta1.ExplanationParameters
Fields
public static final int INTEGRATED_GRADIENTS_ATTRIBUTION_FIELD_NUMBER
Field Value
public static final int OUTPUT_INDICES_FIELD_NUMBER
Field Value
public static final int SAMPLED_SHAPLEY_ATTRIBUTION_FIELD_NUMBER
Field Value
public static final int SIMILARITY_FIELD_NUMBER
Field Value
public static final int TOP_K_FIELD_NUMBER
Field Value
public static final int XRAI_ATTRIBUTION_FIELD_NUMBER
Field Value
Methods
public boolean equals(Object obj)
Parameter
Returns
Overrides
public static ExplanationParameters getDefaultInstance()
Returns
public ExplanationParameters getDefaultInstanceForType()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
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;
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;
public ExplanationParameters.MethodCase getMethodCase()
Returns
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_indeices 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;
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_indeices 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;
public Parser<ExplanationParameters> getParserForType()
Returns
Overrides
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;
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;
public int getSerializedSize()
Returns
Overrides
public Similarity getSimilarity()
Similarity explainability that returns the nearest neighbors from the
provided dataset.
.google.cloud.aiplatform.v1beta1.Similarity similarity = 7;
public SimilarityOrBuilder getSimilarityOrBuilder()
Similarity explainability that returns the nearest neighbors from the
provided dataset.
.google.cloud.aiplatform.v1beta1.Similarity similarity = 7;
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;
| Type | Description |
| int | The topK.
|
public final UnknownFieldSet getUnknownFields()
Returns
Overrides
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;
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;
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;
| Type | Description |
| boolean | Whether the integratedGradientsAttribution field is set.
|
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_indeices 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;
| Type | Description |
| boolean | Whether the outputIndices field is set.
|
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;
| Type | Description |
| boolean | Whether the sampledShapleyAttribution field is set.
|
public boolean hasSimilarity()
Similarity explainability that returns the nearest neighbors from the
provided dataset.
.google.cloud.aiplatform.v1beta1.Similarity similarity = 7;
| Type | Description |
| boolean | Whether the similarity field is set.
|
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;
| Type | Description |
| boolean | Whether the xraiAttribution field is set.
|
Returns
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public static ExplanationParameters.Builder newBuilder()
Returns
public static ExplanationParameters.Builder newBuilder(ExplanationParameters prototype)
Parameter
Returns
public ExplanationParameters.Builder newBuilderForType()
Returns
protected ExplanationParameters.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Returns
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Returns
Overrides
public static ExplanationParameters parseDelimitedFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationParameters parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationParameters parseFrom(byte[] data)
Parameter
| Name | Description |
| data | byte[]
|
Returns
Exceptions
public static ExplanationParameters parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationParameters parseFrom(ByteString data)
Parameter
Returns
Exceptions
public static ExplanationParameters parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationParameters parseFrom(CodedInputStream input)
Parameter
Returns
Exceptions
public static ExplanationParameters parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationParameters parseFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationParameters parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationParameters parseFrom(ByteBuffer data)
Parameter
Returns
Exceptions
public static ExplanationParameters parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static Parser<ExplanationParameters> parser()
Returns
public ExplanationParameters.Builder toBuilder()
Returns
public void writeTo(CodedOutputStream output)
Parameter
Overrides
Exceptions
