public static final class IntegratedGradientsAttribution.Builder extends GeneratedMessageV3.Builder<IntegratedGradientsAttribution.Builder> 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
Inherited Members
com.google.protobuf.GeneratedMessageV3.Builder.getUnknownFieldSetBuilder()
com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownLengthDelimitedField(int,com.google.protobuf.ByteString)
com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownVarintField(int,int)
com.google.protobuf.GeneratedMessageV3.Builder.parseUnknownField(com.google.protobuf.CodedInputStream,com.google.protobuf.ExtensionRegistryLite,int)
com.google.protobuf.GeneratedMessageV3.Builder.setUnknownFieldSetBuilder(com.google.protobuf.UnknownFieldSet.Builder)
Static Methods
public static final Descriptors.Descriptor getDescriptor()
Methods
public IntegratedGradientsAttribution.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Overrides
public IntegratedGradientsAttribution build()
public IntegratedGradientsAttribution buildPartial()
public IntegratedGradientsAttribution.Builder clear()
Overrides
public IntegratedGradientsAttribution.Builder clearBlurBaselineConfig()
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;
public IntegratedGradientsAttribution.Builder clearField(Descriptors.FieldDescriptor field)
Overrides
public IntegratedGradientsAttribution.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Overrides
public IntegratedGradientsAttribution.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.v1beta1.SmoothGradConfig smooth_grad_config = 2;
public IntegratedGradientsAttribution.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 within the desired error range.
Valid range of its value is [1, 100], inclusively.
int32 step_count = 1 [(.google.api.field_behavior) = REQUIRED];
public IntegratedGradientsAttribution.Builder clone()
Overrides
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;
public BlurBaselineConfig.Builder getBlurBaselineConfigBuilder()
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;
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;
public IntegratedGradientsAttribution getDefaultInstanceForType()
public Descriptors.Descriptor getDescriptorForType()
Overrides
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;
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.v1beta1.SmoothGradConfig smooth_grad_config = 2;
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;
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 |
|---|
| Type | Description |
int | The stepCount.
|
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 |
|---|
| Type | Description |
boolean | Whether the blurBaselineConfig field is set.
|
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 |
|---|
| Type | Description |
boolean | Whether the smoothGradConfig field is set.
|
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public IntegratedGradientsAttribution.Builder mergeBlurBaselineConfig(BlurBaselineConfig value)
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;
public IntegratedGradientsAttribution.Builder mergeFrom(IntegratedGradientsAttribution other)
public IntegratedGradientsAttribution.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Overrides
public IntegratedGradientsAttribution.Builder mergeFrom(Message other)
| Parameter |
|---|
| Name | Description |
other | Message
|
Overrides
public IntegratedGradientsAttribution.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.v1beta1.SmoothGradConfig smooth_grad_config = 2;
public final IntegratedGradientsAttribution.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Overrides
public IntegratedGradientsAttribution.Builder setBlurBaselineConfig(BlurBaselineConfig value)
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;
public IntegratedGradientsAttribution.Builder setBlurBaselineConfig(BlurBaselineConfig.Builder builderForValue)
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;
public IntegratedGradientsAttribution.Builder setField(Descriptors.FieldDescriptor field, Object value)
Overrides
public IntegratedGradientsAttribution.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Overrides
public IntegratedGradientsAttribution.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.v1beta1.SmoothGradConfig smooth_grad_config = 2;
public IntegratedGradientsAttribution.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.v1beta1.SmoothGradConfig smooth_grad_config = 2;
public IntegratedGradientsAttribution.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 within the desired error range.
Valid range of its value is [1, 100], inclusively.
int32 step_count = 1 [(.google.api.field_behavior) = REQUIRED];
| Parameter |
|---|
| Name | Description |
value | int
The stepCount to set.
|
public final IntegratedGradientsAttribution.Builder setUnknownFields(UnknownFieldSet unknownFields)
Overrides
