Class IntegratedGradientsAttribution (3.20.0)

public final class IntegratedGradientsAttribution extends GeneratedMessageV3 implements IntegratedGradientsAttributionOrBuilder

An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

Protobuf type google.cloud.aiplatform.v1beta1.IntegratedGradientsAttribution

Inheritance

Object > AbstractMessageLite<MessageType,BuilderType> > AbstractMessage > GeneratedMessageV3 > IntegratedGradientsAttribution

Static Fields

BLUR_BASELINE_CONFIG_FIELD_NUMBER

public static final int BLUR_BASELINE_CONFIG_FIELD_NUMBER
Field Value
TypeDescription
int

SMOOTH_GRAD_CONFIG_FIELD_NUMBER

public static final int SMOOTH_GRAD_CONFIG_FIELD_NUMBER
Field Value
TypeDescription
int

STEP_COUNT_FIELD_NUMBER

public static final int STEP_COUNT_FIELD_NUMBER
Field Value
TypeDescription
int

Static Methods

getDefaultInstance()

public static IntegratedGradientsAttribution getDefaultInstance()
Returns
TypeDescription
IntegratedGradientsAttribution

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
TypeDescription
Descriptor

newBuilder()

public static IntegratedGradientsAttribution.Builder newBuilder()
Returns
TypeDescription
IntegratedGradientsAttribution.Builder

newBuilder(IntegratedGradientsAttribution prototype)

public static IntegratedGradientsAttribution.Builder newBuilder(IntegratedGradientsAttribution prototype)
Parameter
NameDescription
prototypeIntegratedGradientsAttribution
Returns
TypeDescription
IntegratedGradientsAttribution.Builder

parseDelimitedFrom(InputStream input)

public static IntegratedGradientsAttribution parseDelimitedFrom(InputStream input)
Parameter
NameDescription
inputInputStream
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static IntegratedGradientsAttribution parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
IOException

parseFrom(byte[] data)

public static IntegratedGradientsAttribution parseFrom(byte[] data)
Parameter
NameDescription
databyte[]
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static IntegratedGradientsAttribution parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
databyte[]
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteString data)

public static IntegratedGradientsAttribution parseFrom(ByteString data)
Parameter
NameDescription
dataByteString
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static IntegratedGradientsAttribution parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
dataByteString
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static IntegratedGradientsAttribution parseFrom(CodedInputStream input)
Parameter
NameDescription
inputCodedInputStream
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static IntegratedGradientsAttribution parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
IOException

parseFrom(InputStream input)

public static IntegratedGradientsAttribution parseFrom(InputStream input)
Parameter
NameDescription
inputInputStream
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static IntegratedGradientsAttribution parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
IOException

parseFrom(ByteBuffer data)

public static IntegratedGradientsAttribution parseFrom(ByteBuffer data)
Parameter
NameDescription
dataByteBuffer
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static IntegratedGradientsAttribution parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
dataByteBuffer
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
IntegratedGradientsAttribution
Exceptions
TypeDescription
InvalidProtocolBufferException

parser()

public static Parser<IntegratedGradientsAttribution> parser()
Returns
TypeDescription
Parser<IntegratedGradientsAttribution>

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
NameDescription
objObject
Returns
TypeDescription
boolean
Overrides

getBlurBaselineConfig()

public BlurBaselineConfig getBlurBaselineConfig()

Config for IG with blur baseline.

When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383

.google.cloud.aiplatform.v1beta1.BlurBaselineConfig blur_baseline_config = 3;

Returns
TypeDescription
BlurBaselineConfig

The blurBaselineConfig.

getBlurBaselineConfigOrBuilder()

public BlurBaselineConfigOrBuilder getBlurBaselineConfigOrBuilder()

Config for IG with blur baseline.

When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383

.google.cloud.aiplatform.v1beta1.BlurBaselineConfig blur_baseline_config = 3;

Returns
TypeDescription
BlurBaselineConfigOrBuilder

getDefaultInstanceForType()

public IntegratedGradientsAttribution getDefaultInstanceForType()
Returns
TypeDescription
IntegratedGradientsAttribution

getParserForType()

public Parser<IntegratedGradientsAttribution> getParserForType()
Returns
TypeDescription
Parser<IntegratedGradientsAttribution>
Overrides

getSerializedSize()

public int getSerializedSize()
Returns
TypeDescription
int
Overrides

getSmoothGradConfig()

public SmoothGradConfig getSmoothGradConfig()

Config for SmoothGrad approximation of gradients.

When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf

.google.cloud.aiplatform.v1beta1.SmoothGradConfig smooth_grad_config = 2;

Returns
TypeDescription
SmoothGradConfig

The smoothGradConfig.

getSmoothGradConfigOrBuilder()

public SmoothGradConfigOrBuilder getSmoothGradConfigOrBuilder()

Config for SmoothGrad approximation of gradients.

When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf

.google.cloud.aiplatform.v1beta1.SmoothGradConfig smooth_grad_config = 2;

Returns
TypeDescription
SmoothGradConfigOrBuilder

getStepCount()

public int getStepCount()

Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range.

Valid range of its value is [1, 100], inclusively.

int32 step_count = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
TypeDescription
int

The stepCount.

hasBlurBaselineConfig()

public boolean hasBlurBaselineConfig()

Config for IG with blur baseline.

When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383

.google.cloud.aiplatform.v1beta1.BlurBaselineConfig blur_baseline_config = 3;

Returns
TypeDescription
boolean

Whether the blurBaselineConfig field is set.

hasSmoothGradConfig()

public boolean hasSmoothGradConfig()

Config for SmoothGrad approximation of gradients.

When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf

.google.cloud.aiplatform.v1beta1.SmoothGradConfig smooth_grad_config = 2;

Returns
TypeDescription
boolean

Whether the smoothGradConfig field is set.

hashCode()

public int hashCode()
Returns
TypeDescription
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

newBuilderForType()

public IntegratedGradientsAttribution.Builder newBuilderForType()
Returns
TypeDescription
IntegratedGradientsAttribution.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected IntegratedGradientsAttribution.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
NameDescription
parentBuilderParent
Returns
TypeDescription
IntegratedGradientsAttribution.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
NameDescription
unusedUnusedPrivateParameter
Returns
TypeDescription
Object
Overrides

toBuilder()

public IntegratedGradientsAttribution.Builder toBuilder()
Returns
TypeDescription
IntegratedGradientsAttribution.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
NameDescription
outputCodedOutputStream
Overrides
Exceptions
TypeDescription
IOException