dival.reconstructors.learnedpd_reconstructor module

class dival.reconstructors.learnedpd_reconstructor.LearnedPDReconstructor(ray_trafo, **kwargs)

Bases: dival.reconstructors.standard_learned_reconstructor.StandardLearnedReconstructor

CT reconstructor applying a learned primal dual iterative scheme (1).

References

1

Jonas Adler & Ozan Öktem (2018). Learned Primal-Dual Reconstruction. IEEE Transactions on Medical Imaging, 37(6), 1322-1332.

HYPER_PARAMS = {'batch_norm': {'default': False, 'retrain': True}, 'batch_size': {'default': 5, 'retrain': True}, 'epochs': {'default': 20, 'retrain': True}, 'init_fbp': {'default': False, 'retrain': True}, 'init_filter_type': {'default': 'Hann', 'retrain': True}, 'init_frequency_scaling': {'default': 0.4, 'retrain': True}, 'internal_ch': {'default': 32, 'retrain': True}, 'kernel_size': {'default': 3, 'retrain': True}, 'lr': {'default': 0.001, 'retrain': True}, 'lr_min': {'default': 0.0, 'retrain': True}, 'lrelu_coeff': {'default': 0.2, 'retrain': True}, 'ndual': {'default': 5, 'retrain': True}, 'niter': {'default': 10, 'retrain': True}, 'nlayer': {'default': 3, 'retrain': True}, 'normalize_by_opnorm': {'default': True, 'retrain': True}, 'nprimal': {'default': 5, 'retrain': True}, 'prelu': {'default': True, 'retrain': True}, 'use_sigmoid': {'default': False, 'retrain': True}}

__init__(ray_trafo, **kwargs)

Parameters

• ray_trafo (odl.tomo.RayTransform) – Ray transform (the forward operator).

• keyword arguments are passed to super()__init__() (Further) –

init_model()

Initialize model. Called in train() after calling init_transform(), but before calling init_optimizer() and init_scheduler().

init_optimizer(dataset_train)

Initialize the optimizer. Called in train(), after calling init_transform() and init_model(), but before calling init_scheduler().

Parameters

dataset_train (torch.utils.data.Dataset) – The training (torch) dataset constructed in train().

init_scheduler(dataset_train)

Initialize the learning rate scheduler. Called in train(), after calling init_transform(), init_model() and init_optimizer().

Parameters

dataset_train (torch.utils.data.Dataset) – The training (torch) dataset constructed in train().

property batch_norm

property batch_size

property epochs

property init_fbp

property init_filter_type

property init_frequency_scaling

property internal_ch

property kernel_size

property lr

property lr_min

property lrelu_coeff

property ndual

property niter

property nlayer

property normalize_by_opnorm

property nprimal

property prelu

property use_sigmoid