GoogleCloudMlV1ExplanationConfig class
Message holding configuration options for explaining model predictions. There are three feature attribution methods supported for TensorFlow models: integrated gradients, sampled Shapley, and XRAI. Learn more about feature attributions.
Constructors
Properties
- hashCode → int
-
The hash code for this object. [...]
read-only, inherited
- integratedGradientsAttribution ↔ GoogleCloudMlV1IntegratedGradientsAttribution
-
Attributes credit by computing the Aumann-Shapley value taking advantage
of the model's fully differentiable structure. Refer to this paper for
more details: https://arxiv.org/abs/1703.01365
read / write
- runtimeType → Type
-
A representation of the runtime type of the object.
read-only, inherited
- sampledShapleyAttribution ↔ GoogleCloudMlV1SampledShapleyAttribution
-
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.
read / write
- xraiAttribution ↔ GoogleCloudMlV1XraiAttribution
-
Attributes credit by computing the XRAI taking advantage of the model's
fully differentiable structure. Refer to this paper for more details:
https://arxiv.org/abs/1906.02825 Currently only implemented for models
with natural image inputs.
read / write
Methods
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a non-existent method or property is accessed. [...]
inherited
-
toJson(
) → Map< String, Object> -
toString(
) → String -
Returns a string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator. [...]
inherited