Inference mode (Inference Overlay)

Icon	Attribute	Unit	Range	Description	Default value
	INFERENCE_MODE	nominal value	0 or 1	The type of inference used by the configured Region-based Convolutional Neural Network of an Inference Overlay.	0 (Classification)

Animation of inference with a moving window, BBox detection and a stride of 50%.

0.	Classification: Classifies an image by predicting the probability that it contains specific features, such as a tree or solar panel.
1.	BBox detection: detects several features in an image, including the probability it is a particular feature and where it is located.

Notes

• Trained Region-based Convolutional Neural Networks can override the default value of this attribute, by specifying it in the meta data using the INFERENCE_MODE attribute name as its key.

---

Inference Overlay

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