You are here: Start » AVLDL.DeepLearning_SegmentInstances Method

AVLDL.DeepLearning_SegmentInstances Method

Namespace:AvlNet.DeepLearning
Assembly:AvlDl.Net.dll

Syntax

public static void DeepLearning_SegmentInstances
(
	AvlNet.DeepLearning.DeepLearningConnectionState ioState,
	AvlNet.Image inImage,
	NullableRef<AvlNet.Region> inRoi,
	string inDeepModel,
	float? inMinDetectionScore,
	int? inMaxObjectsCount,
	IList<AvlNet.Box> outBoundingBoxes,
	IList<int> outClassIds,
	IList<string> outClassNames,
	IList<float> outScores,
	IList<AvlNet.Region> outMasks
)

Parameters

Name Type Range Default Description
ioStateAvlNet.DeepLearning.DeepLearningConnectionState
inImageAvlNet.ImageInput image
inRoiAvlNet.NullableRef<AvlNet.Region>Area of interest
inDeepModelstringTrained model
inMinDetectionScorefloat?<0.0f, 1.0f>Minimal score of found objects
inMaxObjectsCountint?<1, INF>Maximal number of found objects
outBoundingBoxesSystem.Collections.Generic.IList<AvlNet.Box>Bounding boxes of found objects
outClassIdsSystem.Collections.Generic.IList<int>Ids of found objects classes
outClassNamesSystem.Collections.Generic.IList<string>Names of found objects classes
outScoresSystem.Collections.Generic.IList<float>Scores of found objects
outMasksSystem.Collections.Generic.IList<AvlNet.Region>Masks of found objects

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_SegmentInstances.

Function Overrides

See also