Package com.google.cloud.aiplatform.v1beta1

Interface IntegratedGradientsAttributionOrBuilder

    • Method Detail

      • getStepCount

        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:
        The stepCount.

      • hasSmoothGradConfig

        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:
        Whether the smoothGradConfig field is set.

      • getSmoothGradConfig

        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;
        Returns:
        The smoothGradConfig.

      • getSmoothGradConfigOrBuilder

        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;

      • hasBlurBaselineConfig

        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:
        Whether the blurBaselineConfig field is set.

      • getBlurBaselineConfig

        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;
        Returns:
        The blurBaselineConfig.

      • getBlurBaselineConfigOrBuilder

        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;