Inference mode (Inference Overlay): Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
| Line 13: | Line 13: | ||
}} | }} | ||
{{article end | {{article end | ||
|notes=*[[Neural Network]]s can override the default value of this attribute. | |notes=*Trained [[Neural Network]]s can override the default value of this attribute, by specifying it in the meta data using the INFERENCE_MODE attribute name as its key. | ||
}} | }} | ||
{{InferenceOverlay nav}} | {{InferenceOverlay nav}} | ||
Revision as of 13:39, 17 December 2024
| Icon | Attribute | Unit | Range | Description | Default value |
|---|---|---|---|---|---|
 |
INFERENCE_MODE | nominal value | The type of inference is applied by the configured Neural Network of an Inference Overlay | 0 (Entire map) |
Animation of inference with a moving window, BBox detection and a stride of 50%.
| 0. | Classification: classifies an image. Predicts label probabilities; the image contains or represents (a) particular type(s) of feature(s). For example a tree or a 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 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.
