Model attributes (Inference Overlay)
Jump to navigation
Jump to search
The Inference Overlay's model calculations depend on a number of calculation-wide parameters. These parameters are available as attributes of the inference overlay and can be modified as such.
| Icon | Attribute | Unit | Range | Description | Default value |
|---|---|---|---|---|---|
 |
BOX_OVERLAP | boolean | 0.0 or 1.0 | Whether bounding boxes of identified features are allowed to overlap. | 1.0 |
 |
INFERENCE_MODE | nominal value | 0.0 or 1.0 | The type of inference is applied by the configured Neural Network of an Inference Overlay | 0 (Entire map) |
 |
MASK_THRESHOLD | decimal | 0.0 to 1.0 | The threshold at which a matched pixel is included in the mask result of an Inference Overlay. | 0.7 |
 |
PRIORITIZE_LABELS | boolean | 0.0 or 1.0 | Whether overlapping identified features should be processed in the order of their label value. | 1.0 |
 |
SCORE_THRESHOLD | decimal | 0.0 or 1.0 | The threshold at which an identified feature or pattern is included in the score result of an Inference Overlay. | 0.95 |
 |
STRIDE_FRACTION | decimal | 0.0 to 1.0 | The fraction (of the input window size) at which the input window should march over the input prequels of an Inference Overlay. | 0.5 |
