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()
andpredict()
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: