Prioritize labels (Inference Overlay): Difference between revisions

From Tygron Preview Support Wiki
Jump to navigation Jump to search
No edit summary
No edit summary
 
Line 3: Line 3:
|attribute=PRIORITIZE_LABELS
|attribute=PRIORITIZE_LABELS
|unit=boolean
|unit=boolean
|description=Whether overlapping identified objects should be processed in the order of their label value.
|description=Whether overlapping identified features should be processed in the order of their label value.
|defaultvalue=1.0
|defaultvalue=1.0
|range=0.0 or 1.0
|range=0.0 or 1.0
Line 11: Line 11:
{{article end
{{article end
|notes=
|notes=
* Identified objects are  
* Identified features are  
* When this option is set to true, the identified objects are sorted based on their label, then on their score and then on their size.
* When this option is set to true, the identified features are sorted based on their label, then on their score and then on their size.
* When this option is set to false, the identified objects are still sorted based on their score and then based on their size.
* When this option is set to false, the identified features are still sorted based on their score and then based on their size.
*{{Neural network metadata|PRIORITIZE_LABELS}}
*{{Neural network metadata|PRIORITIZE_LABELS}}
}}
}}
{{InferenceOverlay nav}}
{{InferenceOverlay nav}}

Latest revision as of 14:00, 17 December 2024

Notes

  • Identified features are
  • When this option is set to true, the identified features are sorted based on their label, then on their score and then on their size.
  • When this option is set to false, the identified features are still sorted based on their score and then based on their size.
  • Trained Neural Networks can override the default value of this attribute, by specifying it in the meta data using the PRIORITIZE_LABELS attribute name as its key.