Class: Google::Cloud::AIPlatform::V1::XraiAttribution
- Inherits:
-
Object
- Object
- Google::Cloud::AIPlatform::V1::XraiAttribution
- Extended by:
- Protobuf::MessageExts::ClassMethods
- Includes:
- Protobuf::MessageExts
- Defined in:
- proto_docs/google/cloud/aiplatform/v1/explanation.rb
Overview
An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825
Supported only by image Models.
Instance Attribute Summary collapse
-
#blur_baseline_config ⇒ ::Google::Cloud::AIPlatform::V1::BlurBaselineConfig
Config for XRAI with blur baseline.
-
#smooth_grad_config ⇒ ::Google::Cloud::AIPlatform::V1::SmoothGradConfig
Config for SmoothGrad approximation of gradients.
-
#step_count ⇒ ::Integer
Required.
Instance Attribute Details
#blur_baseline_config ⇒ ::Google::Cloud::AIPlatform::V1::BlurBaselineConfig
Returns Config for XRAI 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.
359 360 361 362 |
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 359 class XraiAttribution include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#smooth_grad_config ⇒ ::Google::Cloud::AIPlatform::V1::SmoothGradConfig
Returns 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.
359 360 361 362 |
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 359 class XraiAttribution include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#step_count ⇒ ::Integer
Returns 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 met within the desired error range.
Valid range of its value is [1, 100], inclusively.
359 360 361 362 |
# File 'proto_docs/google/cloud/aiplatform/v1/explanation.rb', line 359 class XraiAttribution include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |