Semantic Segmentation Node

S

AI/ML/ONNX

Semantic Segmentation

Segment images into semantic classes using ONNX models. Download models from: DeepLabV3 (https://github.com/onnx/models/tree/main/validated/vision/object_detection_segmentation/duc), FCN (https://github.com/onnx/models/tree/main/validated/vision/object_detection_segmentation/fcn)

semantic_segmentationonnx

Inputs4

Outputs2

Security exposure10/10

Packageonnx

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

No score metadata has been set for this node yet.

Input Pins

4

Input

Execution

exec_in

Initiate Execution

Model

Struct

model

ONNX Model Session

SchemaNodeOnnxSessionNodeOnnxSessionNodeOnnxSession1 fields

session_refstringrequired

Cache ID for Session

Schema enforced

Image

Struct

image_in

Image Object

SchemaNodeImageNodeImageNodeImage1 fields

image_refstringrequired

Schema enforced

Classes

Integer

num_classes

Number of segmentation classes

Default 21

Output Pins

2

Output

Execution

exec_out

Done with the Execution

Mask

Struct

mask

Segmentation mask output

SchemaSegmentationMaskSegmentationMaskSegmentationMask5 fields

widthinteger:uint32required

Width of the mask

format uint32min 0

heightinteger:uint32required

Height of the mask

format uint32min 0

dataArray<integer:uint8>required

Class index for each pixel (flattened, row-major order) For semantic segmentation: class_idx per pixel For instance segmentation: instance_id per pixel

itemsinteger:uint8array item

format uint8min 0max 255

num_classesinteger:uint32required

Number of classes in the segmentation

format uint32min 0

class_labelsarray | null

Optional class labels mapping

itemsstringarray item

Node Info

Internal name

semantic_segmentation

Category

AI/ML/ONNX

Version

1