public final class ExplanationParameters extends GeneratedMessageV3 implements ExplanationParametersOrBuilder
Parameters to configure explaining for Model's predictions.
Protobuf type google.cloud.aiplatform.v1.ExplanationParameters
Inherited Members
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT)
Static Fields
public static final int EXAMPLES_FIELD_NUMBER
Field Value |
---|
Type | Description |
int | |
public static final int INTEGRATED_GRADIENTS_ATTRIBUTION_FIELD_NUMBER
Field Value |
---|
Type | Description |
int | |
public static final int OUTPUT_INDICES_FIELD_NUMBER
Field Value |
---|
Type | Description |
int | |
public static final int SAMPLED_SHAPLEY_ATTRIBUTION_FIELD_NUMBER
Field Value |
---|
Type | Description |
int | |
public static final int TOP_K_FIELD_NUMBER
Field Value |
---|
Type | Description |
int | |
public static final int XRAI_ATTRIBUTION_FIELD_NUMBER
Field Value |
---|
Type | Description |
int | |
Static Methods
public static ExplanationParameters getDefaultInstance()
public static final Descriptors.Descriptor getDescriptor()
public static ExplanationParameters.Builder newBuilder()
public static ExplanationParameters.Builder newBuilder(ExplanationParameters prototype)
public static ExplanationParameters parseDelimitedFrom(InputStream input)
public static ExplanationParameters parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static ExplanationParameters parseFrom(byte[] data)
Parameter |
---|
Name | Description |
data | byte[]
|
public static ExplanationParameters parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
public static ExplanationParameters parseFrom(ByteString data)
public static ExplanationParameters parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
public static ExplanationParameters parseFrom(CodedInputStream input)
public static ExplanationParameters parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public static ExplanationParameters parseFrom(InputStream input)
public static ExplanationParameters parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static ExplanationParameters parseFrom(ByteBuffer data)
public static ExplanationParameters parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
public static Parser<ExplanationParameters> parser()
Methods
public boolean equals(Object obj)
Parameter |
---|
Name | Description |
obj | Object
|
Overrides
public ExplanationParameters getDefaultInstanceForType()
public Examples getExamples()
Example-based explanations that returns the nearest neighbors from the
provided dataset.
.google.cloud.aiplatform.v1.Examples examples = 7;
Returns |
---|
Type | Description |
Examples | The examples.
|
public ExamplesOrBuilder getExamplesOrBuilder()
Example-based explanations that returns the nearest neighbors from the
provided dataset.
.google.cloud.aiplatform.v1.Examples examples = 7;
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;
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.v1.IntegratedGradientsAttribution integrated_gradients_attribution = 2;
public ExplanationParameters.MethodCase getMethodCase()
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 |
---|
Type | Description |
ListValue | The outputIndices.
|
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;
public Parser<ExplanationParameters> getParserForType()
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.v1.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.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;
public int getSerializedSize()
Returns |
---|
Type | Description |
int | |
Overrides
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 |
---|
Type | Description |
int | The topK.
|
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;
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;
public boolean hasExamples()
Example-based explanations that returns the nearest neighbors from the
provided dataset.
.google.cloud.aiplatform.v1.Examples examples = 7;
Returns |
---|
Type | Description |
boolean | Whether the examples field is set.
|
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;
Returns |
---|
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_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 |
---|
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.v1.SampledShapleyAttribution sampled_shapley_attribution = 1;
Returns |
---|
Type | Description |
boolean | Whether the sampledShapleyAttribution 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.v1.XraiAttribution xrai_attribution = 3;
Returns |
---|
Type | Description |
boolean | Whether the xraiAttribution field is set.
|
Returns |
---|
Type | Description |
int | |
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public ExplanationParameters.Builder newBuilderForType()
protected ExplanationParameters.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Overrides
public ExplanationParameters.Builder toBuilder()
public void writeTo(CodedOutputStream output)
Overrides