Class ErrorAnalysisAnnotation (1.24.1)

ErrorAnalysisAnnotation(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Model error analysis for each annotation.

Attributes

NameDescription
attributed_items MutableSequence[google.cloud.aiplatform_v1.types.ErrorAnalysisAnnotation.AttributedItem]
Attributed items for a given annotation, typically representing neighbors from the training sets constrained by the query type.
query_type google.cloud.aiplatform_v1.types.ErrorAnalysisAnnotation.QueryType
The query type used for finding the attributed items.
outlier_score float
The outlier score of this annotated item. Usually defined as the min of all distances from attributed items.
outlier_threshold float
The threshold used to determine if this annotation is an outlier or not.

Inheritance

builtins.object > proto.message.Message > ErrorAnalysisAnnotation

Classes

AttributedItem

AttributedItem(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Attributed items for a given annotation, typically representing neighbors from the training sets constrained by the query type.

QueryType

QueryType(value)

The query type used for finding the attributed items.

Values: QUERY_TYPE_UNSPECIFIED (0): Unspecified query type for model error analysis. ALL_SIMILAR (1): Query similar samples across all classes in the dataset. SAME_CLASS_SIMILAR (2): Query similar samples from the same class of the input sample. SAME_CLASS_DISSIMILAR (3): Query dissimilar samples from the same class of the input sample.