Package com.google.cloud.aiplatform.v1

Class IntegratedGradientsAttribution.Builder

    • Method Detail

      • getDescriptor

        public static final com.google.protobuf.Descriptors.Descriptor getDescriptor()

      • internalGetFieldAccessorTable

        protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
        Specified by:
        internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessageV3.Builder<IntegratedGradientsAttribution.Builder>

      • getDescriptorForType

        public com.google.protobuf.Descriptors.Descriptor getDescriptorForType()
        Specified by:
        getDescriptorForType in interface com.google.protobuf.Message.Builder
        Specified by:
        getDescriptorForType in interface com.google.protobuf.MessageOrBuilder
        Overrides:
        getDescriptorForType in class com.google.protobuf.GeneratedMessageV3.Builder<IntegratedGradientsAttribution.Builder>

      • getDefaultInstanceForType

        public IntegratedGradientsAttribution getDefaultInstanceForType()
        Specified by:
        getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuilder
        Specified by:
        getDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilder

      • build

        public IntegratedGradientsAttribution build()
        Specified by:
        build in interface com.google.protobuf.Message.Builder
        Specified by:
        build in interface com.google.protobuf.MessageLite.Builder

      • buildPartial

        public IntegratedGradientsAttribution buildPartial()
        Specified by:
        buildPartial in interface com.google.protobuf.Message.Builder
        Specified by:
        buildPartial in interface com.google.protobuf.MessageLite.Builder

      • isInitialized

        public final boolean isInitialized()
        Specified by:
        isInitialized in interface com.google.protobuf.MessageLiteOrBuilder
        Overrides:
        isInitialized in class com.google.protobuf.GeneratedMessageV3.Builder<IntegratedGradientsAttribution.Builder>

      • 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:
        getStepCount in interface IntegratedGradientsAttributionOrBuilder
        Returns:
        The stepCount.

      • setStepCount

        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];
        Parameters:
        value - The stepCount to set.
        Returns:
        This builder for chaining.

      • clearStepCount

        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];
        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:
        hasSmoothGradConfig in interface IntegratedGradientsAttributionOrBuilder
        Returns:
        Whether the smoothGradConfig field is set.

      • 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;
        Specified by:
        getSmoothGradConfig in interface IntegratedGradientsAttributionOrBuilder
        Returns:
        The smoothGradConfig.

      • setSmoothGradConfig

        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.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

        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.v1.SmoothGradConfig smooth_grad_config = 2;

      • clearSmoothGradConfig

        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.v1.SmoothGradConfig smooth_grad_config = 2;

      • 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;

      • 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;
        Specified by:
        getSmoothGradConfigOrBuilder in interface IntegratedGradientsAttributionOrBuilder

      • 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:
        hasBlurBaselineConfig in interface IntegratedGradientsAttributionOrBuilder
        Returns:
        Whether the blurBaselineConfig field is set.

      • 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.v1.BlurBaselineConfig blur_baseline_config = 3;
        Specified by:
        getBlurBaselineConfig in interface IntegratedGradientsAttributionOrBuilder
        Returns:
        The blurBaselineConfig.

      • setBlurBaselineConfig

        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.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

        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.v1.BlurBaselineConfig blur_baseline_config = 3;

      • clearBlurBaselineConfig

        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.v1.BlurBaselineConfig blur_baseline_config = 3;

      • getBlurBaselineConfigBuilder

        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.v1.BlurBaselineConfig blur_baseline_config = 3;

      • 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.v1.BlurBaselineConfig blur_baseline_config = 3;
        Specified by:
        getBlurBaselineConfigOrBuilder in interface IntegratedGradientsAttributionOrBuilder