frameworks.ultralytics.services.model.predictor.object_detection

object_detection

Classes:

Name	Description
UltralyticsDetectionModelPredictor	A predictor class that handles inference and result formatting for object detection tasks

UltralyticsDetectionModelPredictor(model)

Bases: ModelPredictor[UltralyticsModel]

A predictor class that handles inference and result formatting for object detection tasks using the Ultralytics framework.

Parameters:

Name	Type	Description	Default
model	UltralyticsModel	The detection model with its weights and configuration loaded.	required

Methods:

Name	Description
run_inference_on_batches	Runs inference on each image batch using the model.
post_process_batches	Converts raw model outputs into structured rectangle predictions.
format_predictions	Transforms raw model predictions into Picsellia-compatible rectangle, label, and confidence objects.
rescale_normalized_box	Rescales a bounding box from normalized coordinates to pixel dimensions.
cast_type_list_to_int	Converts all values in a box list to integers.
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 image batch using the model.

Parameters:

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

Returns:

Type	Description
list[Results]	list[Results]: A list of inference result objects, one per batch.

post_process_batches(image_batches, batch_results, dataset)

Converts raw model outputs into structured rectangle predictions.

Parameters:

Name	Type	Description	Default
image_batches	list[list[str]]	List of image batches.	required
batch_results	list[Results]	Model predictions per batch.	required
dataset	TBaseDataset	Dataset context used for label resolution.	required

Returns:

Type	Description
list[PicselliaRectanglePrediction]	list[PicselliaRectanglePrediction]: Structured prediction results per image.

format_predictions(asset, prediction, dataset)

Transforms raw model predictions into Picsellia-compatible rectangle, label, and confidence objects.

Parameters:

Name	Type	Description	Default
asset	Asset	The asset corresponding to the image.	required
prediction	Results	The prediction results for the image.	required
dataset	TBaseDataset	The dataset used to retrieve label mappings.	required

Returns:

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

rescale_normalized_box(box, width, height) staticmethod

Rescales a bounding box from normalized coordinates to pixel dimensions.

Parameters:

Name	Type	Description	Default
box	list	Normalized box in [x_min, y_min, x_max, y_max] format.	required
width	int	Image width.	required
height	int	Image height.	required

Returns:

Type	Description
list[int]	list[int]: Rescaled box in [x, y, width, height] format.

cast_type_list_to_int(box) staticmethod

Converts all values in a box list to integers.

Parameters:

Name	Type	Description	Default
box	list[float]	Bounding box coordinates.	required

Returns:

Type	Description
list[int]	list[int]: Bounding box with integer values.

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.