frameworks.ultralytics.services.model.predictor.classification

classification

Classes:

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

UltralyticsClassificationModelPredictor(model)

Bases: ModelPredictor[UltralyticsModel]

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

This class performs pre-processing of datasets, runs inference on batches of images, and post-processes the predictions to generate PicselliaClassificationPrediction objects for classification tasks.

Parameters:

Name	Type	Description	Default
model	UltralyticsModel	The context containing the loaded model and its configurations.	required

Methods:

Name	Description
pre_process_dataset	Prepares the dataset by extracting and returning a list of image file paths from the dataset directory.
run_inference_on_batches	Runs inference on each batch of images using the model.
post_process_batches	Post-processes all inference results by matching predictions with assets.
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

pre_process_dataset(dataset)

Prepares the dataset by extracting and returning a list of image file paths from the dataset directory.

Parameters:

Name	Type	Description	Default
dataset	TBaseDataset	The dataset containing image directories structured by class.	required

Returns:

Type	Description
list[str]	list[str]: A list of full image file paths.

run_inference_on_batches(image_batches)

Runs inference on each batch of images using the model.

Parameters:

Name	Type	Description	Default
image_batches	list[list[str]]	Batches of image paths.	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)

Post-processes all inference results by matching predictions with assets.

Parameters:

Name	Type	Description	Default
image_batches	list[list[str]]	List of image batches.	required
batch_results	list[Results]	Corresponding model outputs for each batch.	required
dataset	TBaseDataset	Dataset used to resolve label references.	required

Returns:

Type	Description
list[PicselliaClassificationPrediction]	list[PicselliaClassificationPrediction]: Formatted predictions.

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.