anomalib.models.padim.anomaly_map

Anomaly Map Generator for the PaDiM model implementation.

Module Contents

Classes

AnomalyMapGenerator

Generate Anomaly Heatmap.
class anomalib.models.padim.anomaly_map.AnomalyMapGenerator(image_size: Union[omegaconf.ListConfig, Tuple], sigma: int = 4)[source]

Bases: torch.nn.Module

Generate Anomaly Heatmap.

Parameters

  • image_size (Union[ListConfig, Tuple]) – Size of the input image. The anomaly map is upsampled to this dimension.

  • sigma (int, optional) – Standard deviation for Gaussian Kernel. Defaults to 4.

static compute_distance(embedding: torch.Tensor, stats: List[torch.Tensor]) → torch.Tensor[source]

Compute anomaly score to the patch in position(i,j) of a test image.

Ref: Equation (2), Section III-C of the paper.

Parameters

  • embedding (Tensor) – Embedding Vector

  • stats (List[Tensor]) – Mean and Covariance Matrix of the multivariate Gaussian distribution

Returns

Anomaly score of a test image via mahalanobis distance.

up_sample(distance: torch.Tensor) → torch.Tensor[source]

Up sample anomaly score to match the input image size.

Parameters

distance (Tensor) – Anomaly score computed via the mahalanobis distance.

Returns

Resized distance matrix matching the input image size

smooth_anomaly_map(anomaly_map: torch.Tensor) → torch.Tensor[source]

Apply gaussian smoothing to the anomaly map.

Parameters

anomaly_map (Tensor) – Anomaly score for the test image(s).

Returns

Filtered anomaly scores

compute_anomaly_map(embedding: torch.Tensor, mean: torch.Tensor, inv_covariance: torch.Tensor) → torch.Tensor[source]

Compute anomaly score.

Scores are calculated based on embedding vector, mean and inv_covariance of the multivariate gaussian distribution.

Parameters

  • embedding (Tensor) – Embedding vector extracted from the test set.

  • mean (Tensor) – Mean of the multivariate gaussian distribution

  • inv_covariance (Tensor) – Inverse Covariance matrix of the multivariate gaussian distribution.

Returns

Output anomaly score.

forward(**kwargs)[source]

Returns anomaly_map.

Expects embedding, mean and covariance keywords to be passed explicitly.

Example: >>> anomaly_map_generator = AnomalyMapGenerator(image_size=input_size) >>> output = anomaly_map_generator(embedding=embedding, mean=mean, covariance=covariance)

Raises

ValueError – embedding. mean or covariance keys are not found

Returns

anomaly map

Return type

torch.Tensor