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.
Errors
List of possible exceptions:
Error type | Description |
---|---|
DomainError | Not supported inImage pixel format in DeepLearning_DetectAnomalies1. |
See Also
Models for Deep Learning may be created using Adaptive Vision Deep Learning Editor or using Training Api.