Reference

Encyclopedia MAITEanica.

protocols

protocols.ArrayLike
protocols.image_classification.Augmentation(...)	An augmentation protocol for the image classification AI task.
protocols.image_classification.DataLoader(...)	A dataloader protocol for the image classification AI task providing batch-level data access.
protocols.image_classification.Dataset(...)	A dataset protocol for image classification AI task providing datum-level data access.
protocols.image_classification.Metric(*args, ...)	A metric protocol for the image classification AI task.
protocols.image_classification.Model(*args, ...)	A model protocol for the image classification AI task.
protocols.object_detection.Augmentation(...)	An augmentation protocol for the object detection AI task.
protocols.object_detection.ObjectDetectionTarget(...)	An object-detection target protocol.
protocols.object_detection.DataLoader(*args, ...)	A dataloader protocol for the object detection AI task providing batch-level data access.
protocols.object_detection.Dataset(*args, ...)	A dataset protocol for object detection AI task providing datum-level data access.
protocols.object_detection.Metric(*args, ...)	A metric protocol for the object detection AI task.
protocols.object_detection.Model(*args, **kwargs)	A model protocol for the object detection AI task.

tasks

tasks.augment_dataloader(*, augmentation, ...)	Create an DataLoader of augmented inputs from a Dataset or DataLoader.
tasks.evaluate(*, model[, metric, ...])	Evaluate a model's performance on data according to some metric with optional augmentation.
tasks.predict(*, model[, dataloader, ...])	Make predictions for a given model & data source with optional augmentation.
tasks.evaluate_from_predictions(*, metric, ...)	Evaluate pre-calculated predictions against target (truth) data for some specified metric.

interop

interop.metrics.torchmetrics.TMClassificationMetric(metric)	MAITE-compliant Wrapper for TorchMetrics Classification Metrics.
interop.metrics.torchmetrics.TMDetectionMetric(metric)	MAITE-compliant Wrapper for Torchmetrics Detection Metrics.
interop.models.yolo.YoloObjectDetector(...)	MAITE-wrapped object detection YOLO model.