deel.lip.utils module

Contains utility functions.

deel.lip.utils.evaluate_lip_const(model: tensorflow.python.keras.engine.training.Model, x, eps=0.0001, seed=None)

Evaluate the Lipschitz constant of a model, with the naive method. Please note that the estimation of the lipschitz constant is done locally around input sample. This may not correctly estimate the behaviour in the whole domain.

Parameters

  • model – built keras model used to make predictions

  • x – inputs used to compute the lipschitz constant

  • eps – magnitude of noise to add to input in order to compute the constant

  • seed – seed used when generating the noise ( can be set to None )

Returns

the empirically evaluated lipschitz constant. The computation might also be inaccurate in high dimensional space.

deel.lip.utils.evaluate_lip_const_gen(model: tensorflow.python.keras.engine.training.Model, generator: Generator[Tuple[numpy.ndarray, numpy.ndarray], Any, None], eps=0.0001, seed=None)

Evaluate the Lipschitz constant of a model, with the naive method. Please note that the estimation of the lipschitz constant is done locally around input sample. This may not correctly estimate the behaviour in the whole domain. The computation might also be inaccurate in high dimensional space.

This is the generator version of evaluate_lip_const.

Parameters

  • model – built keras model used to make predictions

  • generator – used to select datapoints where to compute the lipschitz constant

  • eps – magnitude of noise to add to input in order to compute the constant

  • seed – seed used when generating the noise ( can be set to None )

Returns

the empirically evaluated lipschitz constant.

deel.lip.utils.load_model(filepath, custom_objects=None, compile=True) → tensorflow.python.keras.engine.training.Model

Equivalent to load_model from keras, but custom_objects are already known

Parameters

  • filepath – One of the following: - String, path to the saved model - h5py.File object from which to load the model.

  • custom_objects – Optional dictionary mapping names (strings) to custom classes or functions to be considered during deserialization.

  • compile – Boolean, whether to compile the model after loading.

Returns

A Keras model instance. If an optimizer was found

deel.lip.utils.model_from_json(json_string, custom_objects=None) → tensorflow.python.keras.engine.training.Model

Equivalent to model_from_json from keras, but custom_objects are already known.

Parameters

  • json_string – JSON string encoding a model configuration.

  • custom_objects – Optional dictionary mapping names (strings) to custom classes or functions to be considered during deserialization.

Returns

A Keras model instance (uncompiled).

deel.lip.utils.model_from_yaml(yaml_string, custom_objects=None) → tensorflow.python.keras.engine.training.Model

Equivalent to model_from_json from keras, but custom_objects are already known

Parameters

  • yaml_string – YAML string encoding a model configuration.

  • custom_objects – Optional dictionary mapping names (strings) to custom classes or functions to be considered during deserialization.

Returns

A Keras model instance (uncompiled).