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.v1.IntegratedGradientsAttribution
Static Fields
public static final int BLUR_BASELINE_CONFIG_FIELD_NUMBER
Field Value
public static final int SMOOTH_GRAD_CONFIG_FIELD_NUMBER
Field Value
public static final int STEP_COUNT_FIELD_NUMBER
Field Value
Static Methods
public static IntegratedGradientsAttribution getDefaultInstance()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
public static IntegratedGradientsAttribution.Builder newBuilder()
Returns
public static IntegratedGradientsAttribution.Builder newBuilder(IntegratedGradientsAttribution prototype)
Parameter
Returns
public static IntegratedGradientsAttribution parseDelimitedFrom(InputStream input)
Parameter
Returns
Exceptions
public static IntegratedGradientsAttribution parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(byte[] data)
Parameter
| Name | Description |
| data | byte[]
|
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(ByteString data)
Parameter
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(CodedInputStream input)
Parameter
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(InputStream input)
Parameter
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(ByteBuffer data)
Parameter
Returns
Exceptions
public static IntegratedGradientsAttribution parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static Parser<IntegratedGradientsAttribution> parser()
Returns
Methods
public boolean equals(Object obj)
Parameter
Returns
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.v1.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.v1.BlurBaselineConfig blur_baseline_config = 3;
public IntegratedGradientsAttribution getDefaultInstanceForType()
Returns
public Parser<IntegratedGradientsAttribution> getParserForType()
Returns
Overrides
public int getSerializedSize()
Returns
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.v1.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.v1.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];
| Type | Description |
| int | The stepCount.
|
public final UnknownFieldSet getUnknownFields()
Returns
Overrides
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.v1.BlurBaselineConfig blur_baseline_config = 3;
| 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.v1.SmoothGradConfig smooth_grad_config = 2;
| Type | Description |
| boolean | Whether the smoothGradConfig field is set.
|
Returns
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public IntegratedGradientsAttribution.Builder newBuilderForType()
Returns
protected IntegratedGradientsAttribution.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Returns
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Returns
Overrides
public IntegratedGradientsAttribution.Builder toBuilder()
Returns
public void writeTo(CodedOutputStream output)
Parameter
Overrides
Exceptions
