You are here: Start » AVL.NET » AVL.DeepLearning_DetectFeatures
Performs feature classification using trained deep-learning model.
| Namespace: | AvlNet |
|---|---|
| Assembly: | AVL.NET.dll |
Syntax
C++
C#
public static void DeepLearning_DetectFeatures ( AvlNet.DeepLearningConnectionState ioState, AvlNet.Image inImage, string inDeepModel, bool inOverlap, IList<AvlNet.Image> outHeatmaps, AvlNet.Image outFeature1, AvlNet.Image outFeature2, AvlNet.Image outFeature3, AvlNet.Image outFeature4 )
Parameters
| Name | Type | Range | Default | Description | |
|---|---|---|---|---|---|
| ioState | AvlNet.DeepLearningConnectionState | ||||
![]() | inImage | AvlNet.Image | Input image. | ||
![]() | inDeepModel | string | Trained model. | ||
![]() | inOverlap | bool | True | Add tiles overlapping to improve results quality. Default value: True. | |
![]() | outHeatmaps | System.Collections.Generic.IList<AvlNet.Image> | Returns heatmaps for all classes. | ||
![]() | outFeature1 | AvlNet.Image | Returns heatmap for first feature class. | ||
![]() | outFeature2 | AvlNet.Image | Returns heatmap for second feature class or empty image if class is not specified. | ||
![]() | outFeature3 | AvlNet.Image | Returns heatmap for third feature class or empty image if class is not specified. | ||
![]() | outFeature4 | AvlNet.Image | Returns heatmap for fourth feature class or empty image if class is not specified. |
Remarks
- Model provided on inDeepModel input will be loaded to service automatically on first usage of Deep Learning filters.
- Service automatically releases and loads model into its memory. It may result in releasing model previously loaded using DeepLearning_LoadModel filter.
- These filters only communicates with service and cannot be use for parallel computation.
Errors
List of possible exceptions:
| Error type | Description |
|---|---|
| DomainError | Empty image in DeepLearning_DetectFeatures. |
| DomainError | Empty ROI region in DeepLearning_DetectFeatures |
| DomainError | Invalid DeepModel in DeepLearning_DetectFeatures. |
| DomainError | Size of ROI differs from size of image in DeepLearning_DetectFeatures |
Function Overrides
- DeepLearning_DetectFeatures(DeepLearningConnectionState, Image, String, Boolean, IList<Image>)
- DeepLearning_DetectFeatures(DeepLearningConnectionState, Image, NullableRef<Region>, String, Boolean, IList<Image>)
- DeepLearning_DetectFeatures(DeepLearningConnectionState, Image, NullableRef<Region>, String, Boolean, IList<Image>, Image, Image, Image, Image)


