Data

Initialization of Anomaly Dataset Utils.

class otx.algorithms.anomaly.adapters.anomalib.data.OTXAnomalyDataModule(config: Union[DictConfig, ListConfig], dataset: DatasetEntity, task_type: TaskType)

Anomaly DataModule.

This class converts OTX Dataset into Anomalib dataset and stores train/val/test dataloaders.

Args:

config (Union[DictConfig, ListConfig]): Anomalib config dataset (DatasetEntity): OTX SDK Dataset

Example:

>>> from tests.helpers.dataset import OTXAnomalyDatasetGenerator
>>> from otx.utils.data import AnomalyDataModule

>>> dataset_generator = OTXAnomalyDatasetGenerator()
>>> dataset = dataset_generator.generate()
>>> data_module = OTXAnomalyDataModule(config=config, dataset=dataset)
>>> i, data = next(enumerate(data_module.train_dataloader()))
>>> data["image"].shape
torch.Size([32, 3, 256, 256])

predict_dataloader() → Union[DataLoader, List[DataLoader]]

Predict Dataloader.

Returns:

Union[DataLoader, List[DataLoader]]: Predict Dataloader.

setup(stage: Optional[str] = None) → None

Setup Anomaly Data Module.

Args:

stage (Optional[str], optional): train/val/test stages.

Defaults to None.

summary()

Print size of the dataset, number of anomalous images and number of normal images.

test_dataloader() → Union[DataLoader, List[DataLoader]]

Test Dataloader.

Returns:

Union[DataLoader, List[DataLoader]]: Test Dataloader.

train_dataloader() → Union[DataLoader, List[DataLoader], Dict[str, DataLoader]]

Train Dataloader.

Returns:

Union[DataLoader, List[DataLoader], Dict[str, DataLoader]]: Train dataloader.

val_dataloader() → Union[DataLoader, List[DataLoader]]

Validation Dataloader.

Returns:

Union[DataLoader, List[DataLoader]]: Validation Dataloader.