You are here: Start » AVL.NET » AVL.DeepLearning_DetectFeatures Method

AVL.DeepLearning_DetectFeatures Method

Performs feature classification using trained deep-learning model.

Namespace:AvlNet
Assembly:AVL.NET.dll

Syntax

public static void DeepLearning_DetectFeatures(
	ref AvlNet.DeepLearningConnectionState ioState,
	AvlNet.Image inImage,
	string inDeepModel,
	bool inOverlap,
	out AvlNet.Image[] outHeatmaps,
	out AvlNet.Image outFeature1,
	out AvlNet.Image outFeature2,
	out AvlNet.Image outFeature3,
	out AvlNet.Image outFeature4
)

Parameters

Name Type Range Default Description
ioStateAvlNet.DeepLearningConnectionState
inImageAvlNet.ImageInput image.
inDeepModelstringTrained model.
inOverlapboolTrueAdd tiles overlapping to improve results quality. Default value: True.
outHeatmapsAvlNet.ImageReturns heatmaps for all classes.
outFeature1AvlNet.ImageReturns heatmap for first feature class.
outFeature2AvlNet.ImageReturns heatmap for second feature class or empty image if class is not specified.
outFeature3AvlNet.ImageReturns heatmap for third feature class or empty image if class is not specified.
outFeature4AvlNet.ImageReturns heatmap for fourth feature class or empty image if class is not specified.

Errors

Error type Description
DomainError Empty ROI region in DeepLearning_DetectFeatures
DomainError Invalid DeepModel in DeepLearning_DetectFeatures.
DomainError Empty image in DeepLearning_DetectFeatures.
IoError Unable to connect to Deep Learning Service.
IoError Connection with service lost.
IoError Missing results count.
IoError Received invalid results count. Classification aborted.
IoError Missing result.

See also