frameworks.ultralytics.services.model.predictor.segmentation

segmentation

Classes:

Name	Description
UltralyticsSegmentationModelPredictor	A predictor class that handles model inference and result post-processing for segmentation tasks

UltralyticsSegmentationModelPredictor(model)

Bases: ModelPredictor[UltralyticsModel]

A predictor class that handles model inference and result post-processing for segmentation tasks using the Ultralytics framework.

Parameters:

Name	Type	Description	Default
model	UltralyticsModel	The model used to perform inference.	required

Methods:

Name	Description
run_inference_on_batches	Runs inference on each batch of images.
post_process_batches	Converts raw predictions into PicselliaPolygonPrediction objects for each image.
format_predictions	Extracts and formats segmentation predictions into Picsellia types.
format_polygons	Converts a polygon array to a list of integer coordinates.
pre_process_dataset	Extracts all image paths from the dataset's image directory.
prepare_batches
get_picsellia_label	Get or create a PicselliaLabel from a dataset category name.
get_picsellia_confidence	Wrap a confidence score in a PicselliaConfidence object.
get_picsellia_rectangle	Create a PicselliaRectangle from bounding box coordinates.

Attributes:

Name	Type	Description
model	TModel

model = model instance-attribute

run_inference_on_batches(image_batches)

Runs inference on each batch of images.

Parameters:

Name	Type	Description	Default
image_batches	list[list[str]]	A list of image path batches.	required

Returns:

Type	Description
list[Results]	list[Results]: The list of inference results for each batch.

post_process_batches(image_batches, batch_results, dataset)

Converts raw predictions into PicselliaPolygonPrediction objects for each image.

Parameters:

Name	Type	Description	Default
image_batches	list[list[str]]	The original image path batches.	required
batch_results	list[Results]	The inference results for each batch.	required
dataset	TBaseDataset	Dataset used to retrieve asset metadata.	required

Returns:

Type	Description
list[PicselliaPolygonPrediction]	list[PicselliaPolygonPrediction]: Structured predictions ready for evaluation/logging.

format_predictions(prediction, dataset)

Extracts and formats segmentation predictions into Picsellia types.

Parameters:

Name	Type	Description	Default
prediction	Results	A single inference result containing segmentation masks.	required
dataset	TBaseDataset	Dataset used to resolve labels.	required

Returns:

Name	Type	Description
tuple	tuple[list[PicselliaPolygon], list[PicselliaLabel], list[PicselliaConfidence]]	Lists of PicselliaPolygon, PicselliaLabel, and PicselliaConfidence.

format_polygons(polygon) staticmethod

Converts a polygon array to a list of integer coordinates.

Parameters:

Name	Type	Description	Default
polygon	ndarray	Polygon mask as an array of coordinates.	required

Returns:

Type	Description
list[list[int]]	list[list[int]]: Polygon represented as a list of integer point pairs.

pre_process_dataset(dataset)

Extracts all image paths from the dataset's image directory.

Parameters:

Name	Type	Description	Default
dataset	TBaseDataset	The dataset object containing the image directory.	required

Returns:

Type	Description
list[str]	list[str]: A list of file paths to the dataset images.

prepare_batches(image_paths, batch_size)

get_picsellia_label(category_name, dataset)

Get or create a PicselliaLabel from a dataset category name.

Parameters:

Name	Type	Description	Default
category_name	str	The name of the label category.	required
dataset	TBaseDataset	Dataset that provides label access.	required

Returns:

Name	Type	Description
PicselliaLabel	PicselliaLabel	Wrapped label object.

get_picsellia_confidence(confidence)

Wrap a confidence score in a PicselliaConfidence object.

Parameters:

Name	Type	Description	Default
confidence	float	Prediction confidence score.	required

Returns:

Name	Type	Description
PicselliaConfidence	PicselliaConfidence	Wrapped confidence object.

get_picsellia_rectangle(x, y, w, h)

Create a PicselliaRectangle from bounding box coordinates.

Parameters:

Name	Type	Description	Default
x	int	Top-left x-coordinate.	required
y	int	Top-left y-coordinate.	required
w	int	Width of the box.	required
h	int	Height of the box.	required

Returns:

Name	Type	Description
PicselliaRectangle	PicselliaRectangle	Rectangle wrapper for object detection.