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

AVL.DeepLearning_DetectAnomalies Method

Detects anomalies using trained deep-learning model.

Namespace:AvlNet
Assembly:AVL.NET.dll

Syntax

public static void DeepLearning_DetectAnomalies(
	ref AvlNet.DeepLearningConnectionState ioState,
	AvlNet.Image inImage,
	string inDeepModel,
	out AvlNet.Image outHeatmap,
	out bool outIsValid,
	out float outScore,
	out bool outIsConfident,
	out AvlNet.Image outReconstructedImage
)

Parameters

Name Type Range Default Description
ioStateAvlNet.DeepLearningConnectionState
inImageAvlNet.ImageInput image.
inDeepModelstringTrained model.
outHeatmapAvlNet.ImageImage contains heatmaps for each input image channel.
outIsValidboolReturns true if anomaly was not found.
outScorefloatScore of classification.
outIsConfidentboolReturns "false" if score is between T1 and T2.
outReconstructedImageAvlNet.ImageReturns network answer.

Errors

Error type Description
DomainError Invalid DeepModel in DeepLearning_DetectAnomalies.
DomainError Empty image in DeepLearning_DetectAnomalies.
IoError Unable to connect to Deep Learning Service. Please check if service is up and running.
IoError Connection with service lost.
IoError Missing results count.
IoError Invalid error count.
IoError Missing result.
IoError Missing heat map.

See also