alibi_detect.utils.saving module¶

alibi_detect.utils.saving.init_ad_vae(state_dict, vae, model)[source]¶

Initialize AdversarialVAE.

Parameters

state_dict (Dict) – Dictionary containing the parameter values.
vae (tensorflow.keras.Model) – Loaded VAE.
model (tensorflow.keras.Model) – Loaded classification model.

Return type

AdversarialVAE

Returns

Initialized AdversarialVAE instance.

alibi_detect.utils.saving.init_od_aegmm(state_dict, aegmm)[source]¶

Initialize OutlierAEGMM.

Parameters

state_dict (Dict) – Dictionary containing the parameter values.
aegmm (tensorflow.keras.Model) – Loaded AEGMM.

Return type

OutlierAEGMM

Returns

Initialized OutlierAEGMM instance.

alibi_detect.utils.saving.init_od_iforest(state_dict)[source]¶

Initialize isolation forest.

Parameters: state_dict (Dict) – Dictionary containing the parameter values.
Return type: IForest
Returns: Initialized IForest instance.

alibi_detect.utils.saving.init_od_mahalanobis(state_dict)[source]¶

Initialize Mahalanobis.

Parameters: state_dict (Dict) – Dictionary containing the parameter values.
Return type: Mahalanobis
Returns: Initialized Mahalanobis instance.

alibi_detect.utils.saving.init_od_prophet(state_dict)[source]¶

Initialize OutlierProphet.

Parameters: state_dict (Dict) – Dictionary containing the parameter values.
Return type: OutlierProphet
Returns: Initialized OutlierProphet instance.

alibi_detect.utils.saving.init_od_sr(state_dict)[source]¶

Initialize spectral residual detector.

Parameters: state_dict (Dict) – Dictionary containing the parameter values.
Return type: SpectralResidual
Returns: Initialized SpectralResidual instance.

alibi_detect.utils.saving.init_od_vae(state_dict, vae)[source]¶

Initialize OutlierVAE.

Parameters

state_dict (Dict) – Dictionary containing the parameter values.
vae (tensorflow.keras.Model) – Loaded VAE.

Return type

OutlierVAE

Returns

Initialized OutlierVAE instance.

alibi_detect.utils.saving.init_od_vaegmm(state_dict, vaegmm)[source]¶

Initialize OutlierVAEGMM.

Parameters

state_dict (Dict) – Dictionary containing the parameter values.
vaegmm (tensorflow.keras.Model) – Loaded VAEGMM.

Return type

OutlierVAEGMM

Returns

Initialized OutlierVAEGMM instance.

alibi_detect.utils.saving.load_detector(filepath)[source]¶

Load outlier or adversarial detector.

Parameters: filepath (str) – Load directory.
Return type: Union[BaseDetector, AdversarialVAE, IForest, Mahalanobis, OutlierAEGMM, OutlierProphet, OutlierVAE, OutlierVAEGMM, SpectralResidual]
Returns: Loaded outlier or adversarial detector object.

alibi_detect.utils.saving.load_tf_aegmm(filepath, state_dict)[source]¶

Load AEGMM.

Parameters

filepath (str) – Save directory.
state_dict (Dict) – Dictionary containing the n_gmm and recon_features parameters.

Return type

tensorflow.keras.Model

Returns

Loaded AEGMM.

alibi_detect.utils.saving.load_tf_model(filepath)[source]¶

Return type: tensorflow.keras.Model

alibi_detect.utils.saving.load_tf_vae(filepath, state_dict)[source]¶

Load VAE.

Parameters

filepath (str) – Save directory.
state_dict (Dict) – Dictionary containing the latent dimension and beta parameters.

Return type

tensorflow.keras.Model

Returns

Loaded VAE.

alibi_detect.utils.saving.load_tf_vaegmm(filepath, state_dict)[source]¶

Load VAEGMM.

Parameters

filepath (str) – Save directory.
state_dict (Dict) – Dictionary containing the n_gmm, latent_dim and recon_features parameters.

Return type

tensorflow.keras.Model

Returns

Loaded VAEGMM.

alibi_detect.utils.saving.save_detector(detector, filepath)[source]¶

Save outlier or adversarial detector.

Parameters

detector (Union[BaseDetector, AdversarialVAE, IForest, Mahalanobis, OutlierAEGMM, OutlierProphet, OutlierVAE, OutlierVAEGMM, SpectralResidual]) – Detector object.
filepath (str) – Save directory.

Return type

None

alibi_detect.utils.saving.save_tf_aegmm(od, filepath)[source]¶

Save TensorFlow components of OutlierAEGMM.

Parameters

od (OutlierAEGMM) – Outlier detector object.
filepath (str) – Save directory.

Return type

None

alibi_detect.utils.saving.save_tf_model(model, filepath)[source]¶

Save TensorFlow model.

Parameters

model (tensorflow.keras.Model) – A tf.keras Model.
filepath (str) – Save directory.

Return type

None

alibi_detect.utils.saving.save_tf_vae(detector, filepath)[source]¶

Save TensorFlow components of OutlierVAE or AdversarialVAE.

Parameters

detector (Union[OutlierVAE, AdversarialVAE]) – Outlier or adversarial detector object.
filepath (str) – Save directory.

Return type

None

alibi_detect.utils.saving.save_tf_vaegmm(od, filepath)[source]¶

Save TensorFlow components of OutlierVAEGMM.

Parameters

od (OutlierVAEGMM) – Outlier detector object.
filepath (str) – Save directory.

Return type

None

alibi_detect.utils.saving.state_adv_vae(ad)[source]¶

AdversarialVAE parameters to save.

Parameters: ad (AdversarialVAE) – Adversarial detector object.
Return type: Dict

alibi_detect.utils.saving.state_aegmm(od)[source]¶

OutlierAEGMM parameters to save.

Parameters: od (OutlierAEGMM) – Outlier detector object.
Return type: Dict

alibi_detect.utils.saving.state_iforest(od)[source]¶

Isolation forest parameters to save.

Parameters: od (IForest) – Outlier detector object.
Return type: Dict

alibi_detect.utils.saving.state_mahalanobis(od)[source]¶

Mahalanobis parameters to save.

Parameters: od (Mahalanobis) – Outlier detector object.
Return type: Dict

alibi_detect.utils.saving.state_prophet(od)[source]¶

OutlierProphet parameters to save.

Parameters: od (OutlierProphet) – Outlier detector object.
Return type: Dict

alibi_detect.utils.saving.state_sr(od)[source]¶

Spectral residual parameters to save.

Parameters: od (SpectralResidual) – Outlier detector object.
Return type: Dict

alibi_detect.utils.saving.state_vae(od)[source]¶

OutlierVAE parameters to save.

Parameters: od (OutlierVAE) – Outlier detector object.
Return type: Dict

alibi_detect.utils.saving.state_vaegmm(od)[source]¶

OutlierVAEGMM parameters to save.

Parameters: od (OutlierVAEGMM) – Outlier detector object.
Return type: Dict