LensDiscoveryStylePersonAttributes

Description

This message holds person attributes from the Person Interpreter model (go/person-interpreter) and the Style AI Iconic Person Scorer (go/styleai-indexing-g3doc#iconic-person-scorer) for the most iconic person in a style image. Discretization of float values is recommended by CDS for cheaper and more efficient storage. Next ID: 11

Attributes List

This module has the following attributes (case-insensitive ascending order):

Attributes

1. discretizedFaceVisibilityScore (type: integer(), default: nil)
   - The visibility of the face of the most iconic person in the image discretized into range [0, 100].
2. discretizedFemaleConfidence (type: integer(), default: nil)
   -
3. discretizedMaleConfidence (type: integer(), default: nil)
   - Male and female confidence scores are discretized into the [0, 100] range.
4. discretizedPredictedAge (type: integer(), default: nil)
   - Age prediction is rounded to the first decimal place and multiplied by 10 (e.g. 12.3 -> 123). Not populated in Amarna for legal reasons.
5. discretizedVisualSaliencyScore (type: integer(), default: nil)
   - The area ratio of the most iconic person to the whole image discretized into range [0, 100].
6. personBoundingBox (type: GoogleApi.ContentWarehouse.V1.Model.LensDiscoveryStyleBoundingBox, default: nil)
   - Bounding box of the most iconic person in the image.
7. personVisibilityScores (type: GoogleApi.ContentWarehouse.V1.Model.LensDiscoveryStylePersonAttributesPersonVisibilityScores, default: nil)
   -
8. predictedAgeBucket (type: String.t, default: nil)
   - Bucketed version of the predicted age.
9. version (type: String.t, default: nil)
   -

Type

Function

Data sourced from HexDocs : GoogleApi.ContentWarehouse.V1.Model.LensDiscoveryStylePersonAttributes

• ‹ LensDiscoveryStyleBoundingBox
• LensDiscoveryStylePersonAttributesPersonVisibilityScores ›

Possibly related Links