Ctrl+K

Base Datamodules

Base Datamodules#

Anomalib datamodule base class.

class anomalib.data.base.datamodule.AnomalibDataModule(train_batch_size, eval_batch_size, num_workers, val_split_mode, val_split_ratio, test_split_mode=None, test_split_ratio=None, image_size=None, transform=None, train_transform=None, eval_transform=None, seed=None)#

Bases: LightningDataModule, ABC

Base Anomalib data module.

Parameters:

  • train_batch_size (int) – Batch size used by the train dataloader.

  • eval_batch_size (int) – Batch size used by the val and test dataloaders.

  • num_workers (int) – Number of workers used by the train, val and test dataloaders.

  • val_split_mode (ValSplitMode) – Determines how the validation split is obtained. Options: [none, same_as_test, from_test, synthetic]

  • val_split_ratio (float) – Fraction of the train or test images held our for validation.

  • test_split_mode (Optional[TestSplitMode], optional) – Determines how the test split is obtained. Options: [none, from_dir, synthetic]. Defaults to None.

  • test_split_ratio (float) – Fraction of the train images held out for testing. Defaults to None.

  • image_size (tuple[int, int], optional) – Size to which input images should be resized. Defaults to None.

  • transform (Transform, optional) – Transforms that should be applied to the input images. Defaults to None.

  • train_transform (Transform, optional) – Transforms that should be applied to the input images during training. Defaults to None.

  • eval_transform (Transform, optional) – Transforms that should be applied to the input images during evaluation. Defaults to None.

  • seed (int | None, optional) – Seed used during random subset splitting. Defaults to None.

property category: str#

Get the category of the datamodule.

property eval_transform: Transform#

Get the transform that will be passed to the val/test/predict datasets.

If the eval_transform is not set, the engine will request the transform from the model.

property name: str#

Name of the datamodule.

predict_dataloader()#

Use the test dataloader for inference unless overridden.

Return type:

Any

setup(stage=None)#

Set up train, validation and test data.

Parameters:

stage (str | None) – str | None: Train/Val/Test stages. Defaults to None.

Return type:

None

test_dataloader()#

Get test dataloader.

Return type:

Any

train_dataloader()#

Get train dataloader.

Return type:

Any

property train_transform: Transform#

Get the transforms that will be passed to the train dataset.

If the train_transform is not set, the engine will request the transform from the model.

property transform: Transform#

Property that returns the user-specified transform for the datamodule, if any.

This property is accessed by the engine to set the transform for the model. The eval_transform takes precedence over the train_transform, because the transform that we store in the model is the one that should be used during inference.

val_dataloader()#

Get validation dataloader.

Return type:

Any

anomalib.data.base.datamodule.collate_fn(batch)#

Collate bounding boxes as lists.

Bounding boxes are collated as a list of tensors, while the default collate function is used for all other entries.

Parameters:

batch (List) – list of items in the batch where len(batch) is equal to the batch size.

Returns:

Dictionary containing the collated batch information.

Return type:

dict[str, Any]

Contents