MRF.Online package

Submodules

MRF.Online.Data_class module

class MRF.Online.Data_class.Data_class(training_parameters, noise_type, noise_level, minPD, maxPD, sampling, min_values, max_values, t2_wrt_t1, CRBrequired=False)

Bases: MRF.BaseData_class.BaseData_class

Class defining the way the parameters space can be sampled.

dico_save()

Save the parameters of the instance of the class Data_class.

sample()

Define the way the parameters space can be sampled.

MRF.Online.Network module

class MRF.Online.Network.Network(name_model, loss, training_parameters, save_name, data_class, save_samples, validation_settings, projection=None)

Bases: MRF.BaseNetwork.BaseNetwork, MRF.Online.Performances.Performances

Class defining the whole neural network for training. The train method will use online computed fingerprints.

dico_save()

Save the results and the settings of the training.

train(lr=0.001, nameoptimizer='Adam')

Launch the training using the parameter lr as learning rate.

MRF.Online.Network.rescale(a)

MRF.Online.Network.scaling(a)

MRF.Online.Performances module

class MRF.Online.Performances.Performances(validation_settings)

Bases: object

Class designed to handle the computations and the definition of the validation loss and errors.

compute_relative_errors(estimations_validation, parameters, size)

dico_save()

Save the parameters of the instance of the class Performances.

init_validation()

Define the validation dataset.

loss_function(outputs, params, size)

validation_step(estimations_validation)

Compute the loss and the relative errors on the parameters on the validation dataset. The parameter ‘estimation_validation’ represents the estimation of the network for the parameters on the validation dataset.