Package com.google.cloud.aiplatform.v1
Class IntegratedGradientsAttribution.Builder
java.lang.Object
com.google.protobuf.AbstractMessageLite.Builder
com.google.protobuf.AbstractMessage.Builder<BuilderT>
com.google.protobuf.GeneratedMessage.Builder<IntegratedGradientsAttribution.Builder>
com.google.cloud.aiplatform.v1.IntegratedGradientsAttribution.Builder
- All Implemented Interfaces:
IntegratedGradientsAttributionOrBuilder,com.google.protobuf.Message.Builder,com.google.protobuf.MessageLite.Builder,com.google.protobuf.MessageLiteOrBuilder,com.google.protobuf.MessageOrBuilder,Cloneable
- Enclosing class:
- IntegratedGradientsAttribution
public static final class IntegratedGradientsAttribution.Builder
extends com.google.protobuf.GeneratedMessage.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/1703.01365Protobuf type
google.cloud.aiplatform.v1.IntegratedGradientsAttribution-
Method Summary
Modifier and TypeMethodDescriptionbuild()clear()Config for IG with blur baseline.Config for SmoothGrad approximation of gradients.Required.Config for IG with blur baseline.Config for IG with blur baseline.Config for IG with blur baseline.static final com.google.protobuf.Descriptors.Descriptorcom.google.protobuf.Descriptors.DescriptorConfig for SmoothGrad approximation of gradients.Config for SmoothGrad approximation of gradients.Config for SmoothGrad approximation of gradients.intRequired.booleanConfig for IG with blur baseline.booleanConfig for SmoothGrad approximation of gradients.protected com.google.protobuf.GeneratedMessage.FieldAccessorTablefinal booleanConfig for IG with blur baseline.mergeFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) mergeFrom(com.google.protobuf.Message other) Config for SmoothGrad approximation of gradients.Config for IG with blur baseline.setBlurBaselineConfig(BlurBaselineConfig.Builder builderForValue) Config for IG with blur baseline.Config for SmoothGrad approximation of gradients.setSmoothGradConfig(SmoothGradConfig.Builder builderForValue) Config for SmoothGrad approximation of gradients.setStepCount(int value) Required.Methods inherited from class com.google.protobuf.GeneratedMessage.Builder
addRepeatedField, clearField, clearOneof, clone, getAllFields, getField, getFieldBuilder, getOneofFieldDescriptor, getParentForChildren, getRepeatedField, getRepeatedFieldBuilder, getRepeatedFieldCount, getUnknownFields, getUnknownFieldSetBuilder, hasField, hasOneof, internalGetMapField, internalGetMapFieldReflection, internalGetMutableMapField, internalGetMutableMapFieldReflection, isClean, markClean, mergeUnknownFields, mergeUnknownLengthDelimitedField, mergeUnknownVarintField, newBuilderForField, onBuilt, onChanged, parseUnknownField, setField, setRepeatedField, setUnknownFields, setUnknownFieldSetBuilder, setUnknownFieldsProto3Methods inherited from class com.google.protobuf.AbstractMessage.Builder
findInitializationErrors, getInitializationErrorString, internalMergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, mergeFrom, newUninitializedMessageException, toStringMethods inherited from class com.google.protobuf.AbstractMessageLite.Builder
addAll, addAll, mergeDelimitedFrom, mergeDelimitedFrom, mergeFrom, newUninitializedMessageExceptionMethods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, waitMethods inherited from interface com.google.protobuf.Message.Builder
mergeDelimitedFrom, mergeDelimitedFromMethods inherited from interface com.google.protobuf.MessageLite.Builder
mergeFromMethods inherited from interface com.google.protobuf.MessageOrBuilder
findInitializationErrors, getAllFields, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof
-
Method Details
-
getDescriptor
public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() -
internalGetFieldAccessorTable
protected com.google.protobuf.GeneratedMessage.FieldAccessorTable internalGetFieldAccessorTable()- Specified by:
internalGetFieldAccessorTablein classcom.google.protobuf.GeneratedMessage.Builder<IntegratedGradientsAttribution.Builder>
-
clear
- Specified by:
clearin interfacecom.google.protobuf.Message.Builder- Specified by:
clearin interfacecom.google.protobuf.MessageLite.Builder- Overrides:
clearin classcom.google.protobuf.GeneratedMessage.Builder<IntegratedGradientsAttribution.Builder>
-
getDescriptorForType
public com.google.protobuf.Descriptors.Descriptor getDescriptorForType()- Specified by:
getDescriptorForTypein interfacecom.google.protobuf.Message.Builder- Specified by:
getDescriptorForTypein interfacecom.google.protobuf.MessageOrBuilder- Overrides:
getDescriptorForTypein classcom.google.protobuf.GeneratedMessage.Builder<IntegratedGradientsAttribution.Builder>
-
getDefaultInstanceForType
- Specified by:
getDefaultInstanceForTypein interfacecom.google.protobuf.MessageLiteOrBuilder- Specified by:
getDefaultInstanceForTypein interfacecom.google.protobuf.MessageOrBuilder
-
build
- Specified by:
buildin interfacecom.google.protobuf.Message.Builder- Specified by:
buildin interfacecom.google.protobuf.MessageLite.Builder
-
buildPartial
- Specified by:
buildPartialin interfacecom.google.protobuf.Message.Builder- Specified by:
buildPartialin interfacecom.google.protobuf.MessageLite.Builder
-
mergeFrom
- Specified by:
mergeFromin interfacecom.google.protobuf.Message.Builder- Overrides:
mergeFromin classcom.google.protobuf.AbstractMessage.Builder<IntegratedGradientsAttribution.Builder>
-
mergeFrom
-
isInitialized
public final boolean isInitialized()- Specified by:
isInitializedin interfacecom.google.protobuf.MessageLiteOrBuilder- Overrides:
isInitializedin classcom.google.protobuf.GeneratedMessage.Builder<IntegratedGradientsAttribution.Builder>
-
mergeFrom
public IntegratedGradientsAttribution.Builder mergeFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException - Specified by:
mergeFromin interfacecom.google.protobuf.Message.Builder- Specified by:
mergeFromin interfacecom.google.protobuf.MessageLite.Builder- Overrides:
mergeFromin classcom.google.protobuf.AbstractMessage.Builder<IntegratedGradientsAttribution.Builder>- Throws:
IOException
-
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];- Specified by:
getStepCountin interfaceIntegratedGradientsAttributionOrBuilder- Returns:
- The stepCount.
-
setStepCount
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];- Parameters:
value- The stepCount to set.- Returns:
- This builder for chaining.
-
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];- Returns:
- This builder for chaining.
-
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;- Specified by:
hasSmoothGradConfigin interfaceIntegratedGradientsAttributionOrBuilder- Returns:
- Whether the smoothGradConfig field is set.
-
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;- Specified by:
getSmoothGradConfigin interfaceIntegratedGradientsAttributionOrBuilder- Returns:
- The smoothGradConfig.
-
setSmoothGradConfig
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; -
setSmoothGradConfig
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.v1.SmoothGradConfig smooth_grad_config = 2; -
mergeSmoothGradConfig
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; -
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; -
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; -
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;- Specified by:
getSmoothGradConfigOrBuilderin interfaceIntegratedGradientsAttributionOrBuilder
-
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.v1.BlurBaselineConfig blur_baseline_config = 3;- Specified by:
hasBlurBaselineConfigin interfaceIntegratedGradientsAttributionOrBuilder- Returns:
- Whether the blurBaselineConfig field is set.
-
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;- Specified by:
getBlurBaselineConfigin interfaceIntegratedGradientsAttributionOrBuilder- Returns:
- The blurBaselineConfig.
-
setBlurBaselineConfig
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; -
setBlurBaselineConfig
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.v1.BlurBaselineConfig blur_baseline_config = 3; -
mergeBlurBaselineConfig
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; -
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.v1.BlurBaselineConfig blur_baseline_config = 3; -
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.v1.BlurBaselineConfig blur_baseline_config = 3; -
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;- Specified by:
getBlurBaselineConfigOrBuilderin interfaceIntegratedGradientsAttributionOrBuilder
-