esem.model_adaptor.ModelAdaptor

class esem.model_adaptor.ModelAdaptor(model)

Provides a unified interface for all emulation engines within ESEm. Concrete classes must implement both train() and predict() methods.

See the API documentation for a list of concrete classes implementing this interface.

__init__(model)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(model)	Initialize self.
predict(*args, **kwargs)	This is either the tf model which can be called directly, or a generator over the model.predict (in tf, so it’s quick).
train(training_params, training_data[, verbose])	Train on the training data :return: