You are here: Start » AVL.NET » AVL.DeepLearning_ClassifyObject

AVL.DeepLearning_ClassifyObject

Performs whole image classification using a trained deep-learning model.

Namespace:AvlNet
Assembly:AVL.NET.dll

Syntax

C++
C#
 
public static void DeepLearning_ClassifyObject
(
	ref AvlNet.DeepLearningConnectionState ioState,
	AvlNet.Image inImage,
	AvlNet.Region inRoi,
	string inDeepModel,
	out AvlNet.ClassConfidence[] outConfidences,
	out string outClassName,
	out int outClassIndex,
	out float outScore,
	out AvlNet.Image diagRelevanceHeatmap
)

Parameters

Name Type Range Default Description
ioStateAvlNet.DeepLearningConnectionState
inImageAvlNet.ImageInput image.
inRoiAvlNet.RegionArea of interest. Default value: atl::NIL, or null.
inDeepModelstringTrained model.
outConfidencesAvlNet.ClassConfidence[]Returns confidences for all classes.
outClassNamestringReturns name of the class with highest confidence.
outClassIndexintReturns the index of the class with highest confidence.
outScorefloatReturns the value of the highest confidence.
diagRelevanceHeatmapAvlNet.ImageReturns heatmap indicating how strong specific parts of image influenced classification result.

Remarks

  • Model provided on inDeepModel input will be loaded to service automatically on first usage of Deep Learning filters.
  • Service automatically releases and loads model into its memory. It may result in releasing model previously loaded using DeepLearning_LoadModel filter.
  • These filters only communicates with service and cannot be use for parallel computation.

Errors

Error type Description
DomainError Empty ROI region in DeepLearning_ClassifyObject
DomainError Size of ROI differs from size of image in DeepLearning_ClassifyObject
DomainError Invalid DeepModel in DeepLearning_ClassifyObject.
DomainError Empty image in DeepLearning_ClassifyObject.
IoError Missing confidences.
IoError Received invalid number of heatmaps.

See also