Class XraiAttribution.Builder (3.12.0)

public static final class XraiAttribution.Builder extends GeneratedMessageV3.Builder<XraiAttribution.Builder> implements XraiAttributionOrBuilder

An explanation method that redistributes Integrated Gradients attributions 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 Supported only by image Models.

Protobuf type google.cloud.aiplatform.v1.XraiAttribution

Static Methods

getDescriptor()

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

Methods

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public XraiAttribution.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
XraiAttribution.Builder
Overrides

build()

public XraiAttribution build()
Returns
TypeDescription
XraiAttribution

buildPartial()

public XraiAttribution buildPartial()
Returns
TypeDescription
XraiAttribution

clear()

public XraiAttribution.Builder clear()
Returns
TypeDescription
XraiAttribution.Builder
Overrides

clearBlurBaselineConfig()

public XraiAttribution.Builder clearBlurBaselineConfig()

Config for XRAI 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.v1.BlurBaselineConfig blur_baseline_config = 3;

Returns
TypeDescription
XraiAttribution.Builder

clearField(Descriptors.FieldDescriptor field)

public XraiAttribution.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
NameDescription
fieldFieldDescriptor
Returns
TypeDescription
XraiAttribution.Builder
Overrides

clearOneof(Descriptors.OneofDescriptor oneof)

public XraiAttribution.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
NameDescription
oneofOneofDescriptor
Returns
TypeDescription
XraiAttribution.Builder
Overrides

clearSmoothGradConfig()

public XraiAttribution.Builder clearSmoothGradConfig()

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.v1.SmoothGradConfig smooth_grad_config = 2;

Returns
TypeDescription
XraiAttribution.Builder

clearStepCount()

public XraiAttribution.Builder clearStepCount()

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 met 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
XraiAttribution.Builder

This builder for chaining.

clone()

public XraiAttribution.Builder clone()
Returns
TypeDescription
XraiAttribution.Builder
Overrides

getBlurBaselineConfig()

public BlurBaselineConfig getBlurBaselineConfig()

Config for XRAI 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.v1.BlurBaselineConfig blur_baseline_config = 3;

Returns
TypeDescription
BlurBaselineConfig

The blurBaselineConfig.

getBlurBaselineConfigBuilder()

public BlurBaselineConfig.Builder getBlurBaselineConfigBuilder()

Config for XRAI 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.v1.BlurBaselineConfig blur_baseline_config = 3;

Returns
TypeDescription
BlurBaselineConfig.Builder

getBlurBaselineConfigOrBuilder()

public BlurBaselineConfigOrBuilder getBlurBaselineConfigOrBuilder()

Config for XRAI 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.v1.BlurBaselineConfig blur_baseline_config = 3;

Returns
TypeDescription
BlurBaselineConfigOrBuilder

getDefaultInstanceForType()

public XraiAttribution getDefaultInstanceForType()
Returns
TypeDescription
XraiAttribution

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
TypeDescription
Descriptor
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.v1.SmoothGradConfig smooth_grad_config = 2;

Returns
TypeDescription
SmoothGradConfig

The smoothGradConfig.

getSmoothGradConfigBuilder()

public SmoothGradConfig.Builder getSmoothGradConfigBuilder()

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.v1.SmoothGradConfig smooth_grad_config = 2;

Returns
TypeDescription
SmoothGradConfig.Builder

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.v1.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 met 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 XRAI 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.v1.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.v1.SmoothGradConfig smooth_grad_config = 2;

Returns
TypeDescription
boolean

Whether the smoothGradConfig field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

mergeBlurBaselineConfig(BlurBaselineConfig value)

public XraiAttribution.Builder mergeBlurBaselineConfig(BlurBaselineConfig value)

Config for XRAI 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.v1.BlurBaselineConfig blur_baseline_config = 3;

Parameter
NameDescription
valueBlurBaselineConfig
Returns
TypeDescription
XraiAttribution.Builder

mergeFrom(XraiAttribution other)

public XraiAttribution.Builder mergeFrom(XraiAttribution other)
Parameter
NameDescription
otherXraiAttribution
Returns
TypeDescription
XraiAttribution.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public XraiAttribution.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
XraiAttribution.Builder
Overrides Exceptions
TypeDescription
IOException

mergeFrom(Message other)

public XraiAttribution.Builder mergeFrom(Message other)
Parameter
NameDescription
otherMessage
Returns
TypeDescription
XraiAttribution.Builder
Overrides

mergeSmoothGradConfig(SmoothGradConfig value)

public XraiAttribution.Builder mergeSmoothGradConfig(SmoothGradConfig value)

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.v1.SmoothGradConfig smooth_grad_config = 2;

Parameter
NameDescription
valueSmoothGradConfig
Returns
TypeDescription
XraiAttribution.Builder

mergeUnknownFields(UnknownFieldSet unknownFields)

public final XraiAttribution.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
XraiAttribution.Builder
Overrides

setBlurBaselineConfig(BlurBaselineConfig value)

public XraiAttribution.Builder setBlurBaselineConfig(BlurBaselineConfig value)

Config for XRAI 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.v1.BlurBaselineConfig blur_baseline_config = 3;

Parameter
NameDescription
valueBlurBaselineConfig
Returns
TypeDescription
XraiAttribution.Builder

setBlurBaselineConfig(BlurBaselineConfig.Builder builderForValue)

public XraiAttribution.Builder setBlurBaselineConfig(BlurBaselineConfig.Builder builderForValue)

Config for XRAI 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.v1.BlurBaselineConfig blur_baseline_config = 3;

Parameter
NameDescription
builderForValueBlurBaselineConfig.Builder
Returns
TypeDescription
XraiAttribution.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public XraiAttribution.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
XraiAttribution.Builder
Overrides

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public XraiAttribution.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
NameDescription
fieldFieldDescriptor
indexint
valueObject
Returns
TypeDescription
XraiAttribution.Builder
Overrides

setSmoothGradConfig(SmoothGradConfig value)

public XraiAttribution.Builder setSmoothGradConfig(SmoothGradConfig value)

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.v1.SmoothGradConfig smooth_grad_config = 2;

Parameter
NameDescription
valueSmoothGradConfig
Returns
TypeDescription
XraiAttribution.Builder

setSmoothGradConfig(SmoothGradConfig.Builder builderForValue)

public XraiAttribution.Builder setSmoothGradConfig(SmoothGradConfig.Builder builderForValue)

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.v1.SmoothGradConfig smooth_grad_config = 2;

Parameter
NameDescription
builderForValueSmoothGradConfig.Builder
Returns
TypeDescription
XraiAttribution.Builder

setStepCount(int value)

public XraiAttribution.Builder setStepCount(int value)

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 met within the desired error range. Valid range of its value is [1, 100], inclusively.

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

Parameter
NameDescription
valueint

The stepCount to set.

Returns
TypeDescription
XraiAttribution.Builder

This builder for chaining.

setUnknownFields(UnknownFieldSet unknownFields)

public final XraiAttribution.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
XraiAttribution.Builder
Overrides