DeepLearning_DetectAnomalies1


Header:AVLDL.h
Namespace:avl

Detects anomalies using trained deep-learning model.

Syntax

void avl::DeepLearning_DetectAnomalies1
(
	const avl::Image& inImage,
	const avl::DeepModel_AnomalyDetection1& inDeepModel,
	const bool inComputeReconstruction,
	avl::Image& outHeatmap,
	bool& outIsValid,
	float& outScore,
	bool& outIsConfident,
	atl::Optional<avl::Image&> outReconstructedImage = atl::NIL
)

Parameters

Name Type Default Description
inImage const Image& Input image
inDeepModel const DeepModel_AnomalyDetection1& Trained model
inComputeReconstruction const bool True
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 Optional<Image&> NIL Returns network answer

Requirements

For input inImage only pixel formats are supported: 1⨯uint8, 3⨯uint8.

Read more about pixel formats in Image documentation.

Optional Outputs

The computation of following outputs can be switched off by passing value atl::NIL to these parameters: outReconstructedImage.

Read more about Optional Outputs.

Hints

Loading Deep Learning Model may take longer timer. Consider using DeepLearning_LoadModel_AnomalyDetection1 for pre-loading model before execution starts.

Remarks

  • Model provided on inDeepModel input will be loaded to service automatically on first usage of Deep Learning filters.
  • These filters only communicates with service and cannot be use for parallel computation.

See Also

  • Models for Deep Learning may be created using Adaptive Vision Deep Learning Editor or using Training Api.