tf_base

class TensorFlowSession

Bases: object

session = None

classmethod configure_session(gpu_allow_growth=True, gpu_per_process_memory_fraction=None)

classmethod set_keras_session(allow_default=True)

Sets the (previously configured) session for use with keras if it has not been previously been set. If no session has been configured, the parameter allowDefault controls whether it is admissible to create a session with default parameters.

Parameters

allow_default – whether to configure, for the case where no session was previously configured, a new session with the defaults.

class KerasVectorRegressionModel(normalisation_mode: sensai.normalisation.NormalisationMode, loss, metrics, optimiser, batch_size=64, epochs=1000, validation_fraction=0.2)

Bases: sensai.vector_model.VectorRegressionModel, abc.ABC

An abstract simple model which maps vectors to vectors and works on pandas.DataFrames (for inputs and outputs)

__init__(normalisation_mode: sensai.normalisation.NormalisationMode, loss, metrics, optimiser, batch_size=64, epochs=1000, validation_fraction=0.2)

Parameters

• normalisation_mode –

• loss –

• metrics –

• optimiser –

• batch_size –

• epochs –

• validation_fraction –