maite.workflows.predict

maite.workflows.predict(*, model, dataloader=None, dataset=None, batch_size=1, augmentation=None)

Make predictions for a given model & data source with optional augmentation.

Some data source (either a dataloader or a dataset) must be provided or an InvalidArgument exception is raised.

Parameters:

modelSomeModel

Maite Model object.

dataloaderSomeDataloader | None, (default=None)

Compatible maite dataloader.

datasetSomeDataset | None, (default=None)

Compatible maite dataset.

batch_sizeint, (default=1)

Batch size for use with dataset (ignored if dataset=None).

augmentationSomeAugmentation | None, (default=None)

Compatible maite augmentation.

Returns:

tuple[Sequence[SomeTargetBatchType], Sequence[tuple[SomeInputBatchType, SomeTargetBatchType, SomeMetadataBatchType]],

A tuple of the predictions (as a sequence of batches) and a sequence of tuples containing the information associated with each batch.