Saving and Loading

Alibi Detect includes support for saving and loading detectors to disk. To save a detector, simply call the save_detector method and provide a path to a directory (a new one will be created if it doesn't exist):

from alibi_detect.od import OutlierVAE
from alibi_detect.saving import save_detector

od = OutlierVAE(...) 

filepath = './my_detector/'
save_detector(od, filepath)

To load a previously saved detector, use the load_detector method and provide it with the path to the detector's directory:

from alibi_detect.saving import load_detector

filepath = './my_detector/'
od = load_detector(filepath)

Note: When loading a saved detector, a warning will be issued if the runtime alibi-detect version is different from the version used to save the detector. It is highly recommended to use the same alibi-detect, Python and dependency versions as were used to save the detector to avoid potential bugs and incompatibilities.

Formats

Detectors can be saved using two formats:

• Config format: For drift detectors, by default save_detector serializes the detector via a config file named config.toml, stored in filepath. The TOML format is human-readable, which makes the config files useful for record keeping, and allows a detector to be edited before it is reloaded. For more details, see Detector Configuration Files.

• Legacy format: Outlier and adversarial detectors are saved to dill files stored within filepath. Drift detectors can also be saved in this legacy format by running save_detector with legacy=True. Loading is performed in the same way, by simply running load_detector(filepath).

Note: If you save a detector with legacy=True, or load one that was saved with legacy=True, and you are using TensorFlow>2.15, then you must set the environment variable TF_USE_LEGACY_KERAS=1. This is in order to tell TensorFlow to use the legacy Keras 2 implementation to save and load TensorFlow models. See TensorFlow + Keras 2 backwards compatibility section of the Getting Started docs for Keras for more details.

Supported detectors

The following tables list the current state of save/load support for each detector. Adding full support for the remaining detectors is in the Roadmap.

Drift detectors

Detector	Legacy save/load	Config save/load
Kolmogorov-Smirnov	✅	✅
Cramér-von Mises	❌	✅
Fisher's Exact Test	❌	✅
Least-Squares Density Difference	❌	✅
Maximum Mean Discrepancy	✅	✅
Learned Kernel MMD	❌	✅
Chi-Squared	✅	✅
Mixed-type tabular	✅	✅
Classifier	✅	✅
Spot-the-diff	❌	✅
Classifier Uncertainty	❌	✅
Regressor Uncertainty	❌	✅
Online Cramér-von Mises	❌	✅
Online Fisher's Exact Test	❌	✅
Online Least-Squares Density Difference	❌	✅
Online Maximum Mean Discrepancy	❌	✅

Outlier detectors

Adversarial detectors

Supported ML models

Alibi Detect drift detectors offer the option to perform preprocessing with user-defined machine learning models:

model = ... # A TensorFlow model
preprocess_fn = partial(preprocess_drift, model=model, batch_size=128)
cd = MMDDrift(x_ref, backend='tensorflow', p_val=.05, preprocess_fn=preprocess_fn)

Additionally, some detectors are built upon models directly, for example the Classifier drift detector requires a model to be passed as an argument:

cd = ClassifierDrift(x_ref, model, backend='sklearn', p_val=.05, preds_type='probs')

In order for a detector to be saveable and loadable, any models contained within it (or referenced within a detector configuration file) must fall within the family of supported models:

TensorFlow

Alibi Detect supports serialization of any TensorFlow model that can be serialized to the HDF5 format. Custom objects should be pre-registered with register_keras_serializable.

PyTorch

Scikit-learn

Online detectors

Online drift detectors are stateful, with their state updated each timestep t (each time .predict() is called). {func}~alibi_detect.saving.save_detector will save the state of online detectors to disk if t > 0. At load time, {func}~alibi_detect.saving.load_detector will load this state. For example:

from alibi_detect.cd import LSDDDriftOnline
from alibi_detect.saving import save_detector, load_detector

# Init detector (t=0)
dd = LSDDDriftOnline(x_ref, window_size=10, ert=50)

# Run 2 predictions
pred_1 = dd.predict(x_1)  # t=1 
pred_2 = dd.predict(x_2)  # t=2

# Save detector (state will be saved since t>0)
save_detector(dd, filepath)

# Load detector
dd_new = load_detector(filepath)  # detector will start at t=2

To save a clean (stateless) detector, it should be reset before saving:

dd.reset_state()  # reset to t=0
save_detector(dd, filepath)  # save the detector without state