Prioritize labels (Inference Overlay): Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
| Line 14: | Line 14: | ||
* 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 objects 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 objects are still sorted based on their score and then based on their size. | ||
* | *{{Neural network metadata|PRIORITIZE_LABELS}} | ||
}} | }} | ||
{{InferenceOverlay nav}} | {{InferenceOverlay nav}} | ||
Revision as of 13:59, 17 December 2024
| Icon | Attribute | Unit | Range | Description | Default value |
|---|---|---|---|---|---|
 |
PRIORITIZE_LABELS | boolean | 0.0 or 1.0 | Whether overlapping identified objects should be processed in the order of their label value. | 1.0 |
Notes
- Identified objects 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 false, the identified objects 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.
