`anomalib.models.draem.utils.augmenter`¶

Augmenter module to generates out-of-distribution samples for the DRAEM implementation.

Module Contents¶

Class that generates noisy augmentations of input images.

Returns the smallest power of 2 greater than or equal to the input value.

anomalib.models.draem.utils.augmenter.nextpow2(value)[source]¶: Returns the smallest power of 2 greater than or equal to the input value.

class anomalib.models.draem.utils.augmenter.Augmenter(anomaly_source_path: Optional[str] = None)[source]¶

Class that generates noisy augmentations of input images.

Parameters

anomaly_source_path (Optional[str]) – Path to a folder of images that will be used as source of the anomalous
specified (noise. If not) –
instead. (random noise will be used) –

rand_augmenter() → imgaug.augmenters.Sequential[source]¶

Selects 3 random transforms that will be applied to the anomaly source images.

generate_perturbation(height: int, width: int, anomaly_source_path: Optional[str]) → Tuple[numpy.ndarray, numpy.ndarray][source]¶

Generate an image containing a random anomalous perturbation using a source image.

Parameters

height (int) – height of the generated image.
width – (int): width of the generated image.
anomaly_source_path (Optional[str]) – Path to an image file. If not provided, random noise will be used
instead. –

Returns

Image containing a random anomalous perturbation, and the corresponding ground truth anomaly mask.

augment_batch(batch: torch.Tensor) → Tuple[torch.Tensor, torch.Tensor][source]¶

Generate anomalous augmentations for a batch of input images.

Parameters

batch (Tensor) – Batch of input images

Returns