v2026.4.1
All Bundles

DeepLabSession

DeepLab inference session for semantic segmentation. Auto-detects model input dimensions and supports both NCHW and NHWC layouts. Returns per-class coverage percentages and polygon boundaries. Example labels := ["background", "person", "bicycle", "car"]; session := DeepLabSession->New("deeplabv3.onnx"); result := session->Inference(image_bytes, labels); each(cls in result->GetClassifications()) { "{cls->GetName()}: {cls->GetConfidence()}%"->PrintLine(); }; session->Close();

Operations

Close

Closes the session

method : public : Close() ~ Nil

Inference

DeepLab image inference

method : public : Inference(image:Byte[], labels:String[]) ~ API.Onnx.DeepLabResult

Parameters

NameTypeDescription
imageBytewidth width
labelsStringclassification labels

New

Constructor.

New(model:String)

Parameters

NameTypeDescription
modelStringDeepLab model path

New

Constructor.

New(model:String, config:Map<String,String>)

Parameters

NameTypeDescription
modelStringDeepLab model path
configMap<String,String>session configuration parameters