You are here: Start » Function Reference » Deep Learning » DeepLearning_DetectAnomalies

DeepLearning_DetectAnomalies

Detects anomalies using trained deep-learning model.

Syntax

void avl::DeepLearning_DetectAnomalies
(
	DeepLearningConnectionState& ioState,
	const avl::Image& inImage,
	const avl::DeepModel& inDeepModel,
	avl::Image& outHeatmap,
	bool& outIsValid,
	float& outScore,
	bool& outIsConfident,
	avl::Image& outReconstructedImage
)

void DeepLearning_DetectAnomalies
(
	ref DeepLearningConnectionState ioState,
	Image inImage,
	DeepModel inDeepModel,
	out Image outHeatmap,
	out bool outIsValid,
	out float outScore,
	out bool outIsConfident,
	out Image outReconstructedImage
)

Parameters

Name	Type	Description
ioState	DeepLearningConnectionState&	Object used to maintain state of the function.
inImage	const Image&	Input image
inDeepModel	const DeepModel&	Trained model
outHeatmap	Image&	Image contains heatmaps for each input image channel
outIsValid	bool&	Returns true if anomaly was not found
outScore	float&	Score of classification
outIsConfident	bool&	Returns "false" if score is between T1 and T2
outReconstructedImage	Image&	Returns 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.