anomalib.models

Load Anomaly Model.

Subpackages

Package Contents

Classes

Cflow

PL Lightning Module for the CFLOW algorithm.

Dfkde

DFKDE: Deep Feature Kernel Density Estimation.

Dfm

DFM: Deep Featured Kernel Density Estimation.

Draem

DRÆM: A discriminatively trained reconstruction embedding for surface anomaly detection.

Fastflow

PL Lightning Module for the FastFlow algorithm.

Ganomaly

PL Lightning Module for the GANomaly Algorithm.

Padim

PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization.

Patchcore

PatchcoreLightning Module to train PatchCore algorithm.

ReverseDistillation

PL Lightning Module for Reverse Distillation Algorithm.

Stfpm

PL Lightning Module for the STFPM algorithm.
class anomalib.models.Cflow(input_size: Tuple[int, int], backbone: str, layers: List[str], fiber_batch_size: int = 64, decoder: str = 'freia-cflow', condition_vector: int = 128, coupling_blocks: int = 8, clamp_alpha: float = 1.9, permute_soft: bool = False, lr: float = 0.0001)

Bases: anomalib.models.components.AnomalyModule

PL Lightning Module for the CFLOW algorithm.

configure_optimizers(self) → torch.optim.Optimizer

Configures optimizers for each decoder.

Note

This method is used for the existing CLI. When PL CLI is introduced, configure optimizers method will be

deprecated, and optimizers will be configured from either config.yaml file or from CLI.

Returns

Adam optimizer for each decoder

Return type

Optimizer

training_step(self, batch, _)

Training Step of CFLOW.

For each batch, decoder layers are trained with a dynamic fiber batch size. Training step is performed manually as multiple training steps are involved

per batch of input images

Parameters

  • batch – Input batch

  • _ – Index of the batch.

Returns

Loss value for the batch

validation_step(self, batch, _)

Validation Step of CFLOW.

Similar to the training step, encoder features are extracted from the CNN for each batch, and anomaly map is computed.

Parameters

  • batch – Input batch

  • _ – Index of the batch.

Returns

Dictionary containing images, anomaly maps, true labels and masks. These are required in validation_epoch_end for feature concatenation.

class anomalib.models.Dfkde(backbone: str, max_training_points: int = 40000, pre_processing: str = 'scale', n_components: int = 16, threshold_steepness: float = 0.05, threshold_offset: int = 12)

Bases: anomalib.models.components.AnomalyModule

DFKDE: Deep Feature Kernel Density Estimation.

Parameters

  • backbone (str) – Pre-trained model backbone.

  • max_training_points (int, optional) – Number of training points to fit the KDE model. Defaults to 40000.

  • pre_processing (str, optional) – Preprocess features before passing to KDE. Options are between norm and scale. Defaults to “scale”.

  • n_components (int, optional) – Number of PCA components. Defaults to 16.

  • threshold_steepness (float, optional) – Controls how quickly the value saturates around zero. Defaults to 0.05.

  • threshold_offset (float, optional) – Offset of the density function from 0. Defaults to 12.0.

static configure_optimizers()

DFKDE doesn’t require optimization, therefore returns no optimizers.

training_step(self, batch, _batch_idx)

Training Step of DFKDE. For each batch, features are extracted from the CNN.

Parameters

  • batch (Dict[str, Any]) – Batch containing image filename, image, label and mask

  • _batch_idx – Index of the batch.

Returns

Deep CNN features.

on_validation_start(self) → None

Fit a KDE Model to the embedding collected from the training set.

validation_step(self, batch, _)

Validation Step of DFKDE.

Similar to the training step, features are extracted from the CNN for each batch.

Parameters

batch – Input batch

Returns

Dictionary containing probability, prediction and ground truth values.

class anomalib.models.Dfm(backbone: str, layer: str, pooling_kernel_size: int = 4, pca_level: float = 0.97, score_type: str = 'fre')

Bases: anomalib.models.components.AnomalyModule

DFM: Deep Featured Kernel Density Estimation.

Parameters

  • backbone (str) – Backbone CNN network

  • layer (str) – Layer to extract features from the backbone CNN

  • pooling_kernel_size (int, optional) – Kernel size to pool features extracted from the CNN. Defaults to 4.

  • pca_level (float, optional) – Ratio from which number of components for PCA are calculated. Defaults to 0.97.

  • score_type (str, optional) – Scoring type. Options are fre and nll. Defaults to “fre”.

  • nll – for Gaussian modeling, fre: pca feature reconstruction error

static configure_optimizers() → None

DFM doesn’t require optimization, therefore returns no optimizers.

training_step(self, batch, _)

Training Step of DFM.

For each batch, features are extracted from the CNN.

Parameters

  • batch (Dict[str, Tensor]) – Input batch

  • _ – Index of the batch.

Returns

Deep CNN features.

on_validation_start(self) → None

Fit a PCA transformation and a Gaussian model to dataset.

validation_step(self, batch, _)

Validation Step of DFM.

Similar to the training step, features are extracted from the CNN for each batch.

Parameters

batch (List[Dict[str, Any]]) – Input batch

Returns

Dictionary containing FRE anomaly scores and ground-truth.

class anomalib.models.Draem(anomaly_source_path: Optional[str] = None)

Bases: anomalib.models.components.AnomalyModule

DRÆM: A discriminatively trained reconstruction embedding for surface anomaly detection.

Parameters

anomaly_source_path (Optional[str]) – Path to folder that contains the anomaly source images. Random noise will be used if left empty.

training_step(self, batch, _)

Training Step of DRAEM.

Feeds the original image and the simulated anomaly image through the network and computes the training loss.

Parameters

batch (Dict[str, Any]) – Batch containing image filename, image, label and mask

Returns

Loss dictionary

validation_step(self, batch, _)

Validation step of DRAEM. The Softmax predictions of the anomalous class are used as anomaly map.

Parameters

batch – Batch of input images

Returns

Dictionary to which predicted anomaly maps have been added.

class anomalib.models.Fastflow(input_size: Tuple[int, int], backbone: str, flow_steps: int, conv3x3_only: bool = False, hidden_ratio: float = 1.0)

Bases: anomalib.models.components.AnomalyModule

PL Lightning Module for the FastFlow algorithm.

Parameters

  • input_size (Tuple[int, int]) – Model input size.

  • backbone (str) – Backbone CNN network

  • flow_steps (int) – Flow steps.

  • conv3x3_only (bool, optinoal) – Use only conv3x3 in fast_flow model. Defaults to False.

  • hidden_ratio (float, optional) – Ratio to calculate hidden var channels. Defaults to 1.0.

training_step(self, batch, _)

Forward-pass input and return the loss.

Parameters

  • batch (Tensor) – Input batch

  • _batch_idx – Index of the batch.

Returns

Dictionary containing the loss value.

Return type

STEP_OUTPUT

validation_step(self, batch, _)

Forward-pass the input and return the anomaly map.

Parameters

  • batch (Tensor) – Input batch

  • _batch_idx – Index of the batch.

Returns

batch dictionary containing anomaly-maps.

Return type

dict

class anomalib.models.Ganomaly(batch_size: int, input_size: Tuple[int, int], n_features: int, latent_vec_size: int, extra_layers: int = 0, add_final_conv_layer: bool = True, wadv: int = 1, wcon: int = 50, wenc: int = 1, lr: float = 0.0002, beta1: float = 0.5, beta2: float = 0.999)

Bases: anomalib.models.components.AnomalyModule

PL Lightning Module for the GANomaly Algorithm.

Parameters

  • batch_size (int) – Batch size.

  • input_size (Tuple[int,int]) – Input dimension.

  • n_features (int) – Number of features layers in the CNNs.

  • latent_vec_size (int) – Size of autoencoder latent vector.

  • extra_layers (int, optional) – Number of extra layers for encoder/decoder. Defaults to 0.

  • add_final_conv_layer (bool, optional) – Add convolution layer at the end. Defaults to True.

  • wadv (int, optional) – Weight for adversarial loss. Defaults to 1.

  • wcon (int, optional) – Image regeneration weight. Defaults to 50.

  • wenc (int, optional) – Latent vector encoder weight. Defaults to 1.

_reset_min_max(self)

Resets min_max scores.

configure_optimizers(self) → List[torch.optim.Optimizer]

Configures optimizers for each decoder.

Note

This method is used for the existing CLI. When PL CLI is introduced, configure optimizers method will be

deprecated, and optimizers will be configured from either config.yaml file or from CLI.

Returns

Adam optimizer for each decoder

Return type

Optimizer

training_step(self, batch, _, optimizer_idx)

Training step.

Parameters

  • batch (Dict) – Input batch containing images.

  • optimizer_idx (int) – Optimizer which is being called for current training step.

Returns

Loss

Return type

Dict[str, Tensor]

on_validation_start(self) → None

Reset min and max values for current validation epoch.

validation_step(self, batch, _) → Dict[str, torch.Tensor]

Update min and max scores from the current step.

Parameters

batch (Dict[str, Tensor]) – Predicted difference between z and z_hat.

Returns

batch

Return type

Dict[str, Tensor]

validation_epoch_end(self, outputs)

Normalize outputs based on min/max values.

on_test_start(self) → None

Reset min max values before test batch starts.

test_step(self, batch, _)

Update min and max scores from the current step.

test_epoch_end(self, outputs)

Normalize outputs based on min/max values.

_normalize(self, scores: torch.Tensor) → torch.Tensor

Normalize the scores based on min/max of entire dataset.

Parameters

scores (Tensor) – Un-normalized scores.

Returns

Normalized scores.

Return type

Tensor

class anomalib.models.Padim(layers: List[str], input_size: Tuple[int, int], backbone: str)

Bases: anomalib.models.components.AnomalyModule

PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization.

Parameters

  • layers (List[str]) – Layers to extract features from the backbone CNN

  • input_size (Tuple[int, int]) – Size of the model input.

  • backbone (str) – Backbone CNN network

static configure_optimizers()

PADIM doesn’t require optimization, therefore returns no optimizers.

training_step(self, batch, _batch_idx)

Training Step of PADIM. For each batch, hierarchical features are extracted from the CNN.

Parameters

  • batch (Dict[str, Any]) – Batch containing image filename, image, label and mask

  • _batch_idx – Index of the batch.

Returns

Hierarchical feature map

on_validation_start(self) → None

Fit a Gaussian to the embedding collected from the training set.

validation_step(self, batch, _)

Validation Step of PADIM.

Similar to the training step, hierarchical features are extracted from the CNN for each batch.

Parameters

  • batch – Input batch

  • _ – Index of the batch.

Returns

Dictionary containing images, features, true labels and masks. These are required in validation_epoch_end for feature concatenation.

class anomalib.models.Patchcore(input_size: Tuple[int, int], backbone: str, layers: List[str], coreset_sampling_ratio: float = 0.1, num_neighbors: int = 9)

Bases: anomalib.models.components.AnomalyModule

PatchcoreLightning Module to train PatchCore algorithm.

Parameters

  • input_size (Tuple[int, int]) – Size of the model input.

  • backbone (str) – Backbone CNN network

  • layers (List[str]) – Layers to extract features from the backbone CNN

  • coreset_sampling_ratio (float, optional) – Coreset sampling ratio to subsample embedding. Defaults to 0.1.

  • num_neighbors (int, optional) – Number of nearest neighbors. Defaults to 9.

configure_optimizers(self) → None

Configure optimizers.

Returns

Do not set optimizers by returning None.

Return type

None

training_step(self, batch, _batch_idx)

Generate feature embedding of the batch.

Parameters

  • batch (Dict[str, Any]) – Batch containing image filename, image, label and mask

  • _batch_idx (int) – Batch Index

Returns

Embedding Vector

Return type

Dict[str, np.ndarray]

on_validation_start(self) → None

Apply subsampling to the embedding collected from the training set.

validation_step(self, batch, _)

Get batch of anomaly maps from input image batch.

Parameters

  • batch (Dict[str, Any]) – Batch containing image filename, image, label and mask

  • _ (int) – Batch Index

Returns

Image filenames, test images, GT and predicted label/masks

Return type

Dict[str, Any]

class anomalib.models.ReverseDistillation(input_size: Tuple[int, int], backbone: str, layers: List[str], anomaly_map_mode: str, lr: float, beta1: float, beta2: float)

Bases: anomalib.models.components.AnomalyModule

PL Lightning Module for Reverse Distillation Algorithm.

Parameters

  • input_size (Tuple[int, int]) – Size of model input

  • backbone (str) – Backbone of CNN network

  • layers (List[str]) – Layers to extract features from the backbone CNN

configure_optimizers(self)

Configures optimizers for decoder and bottleneck.

Note

This method is used for the existing CLI. When PL CLI is introduced, configure optimizers method will be

deprecated, and optimizers will be configured from either config.yaml file or from CLI.

Returns

Adam optimizer for each decoder

Return type

Optimizer

training_step(self, batch, _) → Dict[str, torch.Tensor]

Training Step of Reverse Distillation Model.

Features are extracted from three layers of the Encoder model. These are passed to the bottleneck layer that are passed to the decoder network. The loss is then calculated based on the cosine similarity between the encoder and decoder features.

Parameters

  • batch (Tensor) – Input batch

  • _ – Index of the batch.

Returns

Feature Map

validation_step(self, batch, _)

Validation Step of Reverse Distillation Model.

Similar to the training step, encoder/decoder features are extracted from the CNN for each batch, and anomaly map is computed.

Parameters

  • batch (Tensor) – Input batch

  • _ – Index of the batch.

Returns

Dictionary containing images, anomaly maps, true labels and masks. These are required in validation_epoch_end for feature concatenation.

class anomalib.models.Stfpm(input_size: Tuple[int, int], backbone: str, layers: List[str])

Bases: anomalib.models.components.AnomalyModule

PL Lightning Module for the STFPM algorithm.

Parameters

  • input_size (Tuple[int, int]) – Size of the model input.

  • backbone (str) – Backbone CNN network

  • layers (List[str]) – Layers to extract features from the backbone CNN

training_step(self, batch, _)

Training Step of STFPM.

For each batch, teacher and student and teacher features are extracted from the CNN.

Parameters

  • batch (Tensor) – Input batch

  • _ – Index of the batch.

Returns

Hierarchical feature map

validation_step(self, batch, _)

Validation Step of STFPM.

Similar to the training step, student/teacher features are extracted from the CNN for each batch, and anomaly map is computed.

Parameters

  • batch (Tensor) – Input batch

  • _ – Index of the batch.

Returns

Dictionary containing images, anomaly maps, true labels and masks. These are required in validation_epoch_end for feature concatenation.