datumaro.plugins.explorer#

Classes

ExplorerLauncher([description, weights, ...])

class datumaro.plugins.explorer.ExplorerLauncher(description=None, weights=None, interpreter=None, model_dir=None, model_name=None, output_layers=None, device=None)[source]#

Bases: OpenvinoLauncher

infer_text(text: str, use_prompt: bool = True) → HashKey[source]#

infer_item(item: DatasetItem) → HashKey[source]#

launch(batch: Sequence[DatasetItem]) → List[List[Annotation]][source]#

Launch to obtain the inference outputs of items.

Parameters:

inputs – batch of Datasetitems
stack – If true, launch inference for the stacked input for the batch-wise dimension Otherwise, launch inference for each input.

Returns:

A list of annotation list. Each annotation list is mapped to the input DatasetItem. These annotation list are pseudo-labels obtained by the model inference.

type_check(item)[source]#

Check the media type of dataset item.

If False, the item is excluded from the input batch.