Model attributes (Inference Overlay)

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		The type of inference is applied by the configured Neural Network of an Inference Overlay	0 (Entire map)
	MASK_THRESHOLD	decimal		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		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

---

Inference Overlay

Inference Overlay

Tutorials

Overview

Theory

Benchmarks

Group

Model attributes

Inference

Neural Network • Input tensor • Output tensor

Model attributes

Box overlap • Inference mode • Mask threshold • Prioritize labels • Score threshold • Stride fraction

Prequels

A • B

Result types

Boxes • Labels • Masks • Scores • Debug gt instances • Center points

Neural Networks

Foliage • Solar panels