Class ErrorAnalysisAnnotation (1.50.0)

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

Model error analysis for each annotation.

Attributes

Name Description
attributed_items MutableSequence[google.cloud.aiplatform_v1beta1.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_v1beta1.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.

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.

Enum 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.

Methods

ErrorAnalysisAnnotation

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

Model error analysis for each annotation.