Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::ExplanationParameters.
Parameters to configure explaining for Model's predictions.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#examples
def examples() -> ::Google::Cloud::AIPlatform::V1::Examples
- (::Google::Cloud::AIPlatform::V1::Examples) — Example-based explanations that returns the nearest neighbors from the provided dataset.
#examples=
def examples=(value) -> ::Google::Cloud::AIPlatform::V1::Examples
- value (::Google::Cloud::AIPlatform::V1::Examples) — Example-based explanations that returns the nearest neighbors from the provided dataset.
- (::Google::Cloud::AIPlatform::V1::Examples) — Example-based explanations that returns the nearest neighbors from the provided dataset.
#integrated_gradients_attribution
def integrated_gradients_attribution() -> ::Google::Cloud::AIPlatform::V1::IntegratedGradientsAttribution
- (::Google::Cloud::AIPlatform::V1::IntegratedGradientsAttribution) — An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
#integrated_gradients_attribution=
def integrated_gradients_attribution=(value) -> ::Google::Cloud::AIPlatform::V1::IntegratedGradientsAttribution
- value (::Google::Cloud::AIPlatform::V1::IntegratedGradientsAttribution) — An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- (::Google::Cloud::AIPlatform::V1::IntegratedGradientsAttribution) — An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
#output_indices
def output_indices() -> ::Google::Protobuf::ListValue
-
(::Google::Protobuf::ListValue) — If populated, only returns attributions that have
output_index
contained in output_indices. It must be an ndarray of integers, with the
same shape of the output it's explaining.
If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs.
Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
#output_indices=
def output_indices=(value) -> ::Google::Protobuf::ListValue
-
value (::Google::Protobuf::ListValue) — If populated, only returns attributions that have
output_index
contained in output_indices. It must be an ndarray of integers, with the
same shape of the output it's explaining.
If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs.
Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
-
(::Google::Protobuf::ListValue) — If populated, only returns attributions that have
output_index
contained in output_indices. It must be an ndarray of integers, with the
same shape of the output it's explaining.
If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs.
Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
#sampled_shapley_attribution
def sampled_shapley_attribution() -> ::Google::Cloud::AIPlatform::V1::SampledShapleyAttribution
- (::Google::Cloud::AIPlatform::V1::SampledShapleyAttribution) — An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
#sampled_shapley_attribution=
def sampled_shapley_attribution=(value) -> ::Google::Cloud::AIPlatform::V1::SampledShapleyAttribution
- value (::Google::Cloud::AIPlatform::V1::SampledShapleyAttribution) — An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- (::Google::Cloud::AIPlatform::V1::SampledShapleyAttribution) — An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
#top_k
def top_k() -> ::Integer
- (::Integer) — If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
#top_k=
def top_k=(value) -> ::Integer
- value (::Integer) — If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- (::Integer) — If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
#xrai_attribution
def xrai_attribution() -> ::Google::Cloud::AIPlatform::V1::XraiAttribution
-
(::Google::Cloud::AIPlatform::V1::XraiAttribution) — An attribution method that redistributes Integrated Gradients
attribution 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
XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
#xrai_attribution=
def xrai_attribution=(value) -> ::Google::Cloud::AIPlatform::V1::XraiAttribution
-
value (::Google::Cloud::AIPlatform::V1::XraiAttribution) — An attribution method that redistributes Integrated Gradients
attribution 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
XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
-
(::Google::Cloud::AIPlatform::V1::XraiAttribution) — An attribution method that redistributes Integrated Gradients
attribution 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
XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.