dival.reconstructors.learnedgd_reconstructor module

class dival.reconstructors.learnedgd_reconstructor.LearnedGDReconstructor(ray_trafo, **kwargs)

Bases: dival.reconstructors.standard_learned_reconstructor.StandardLearnedReconstructor

CT reconstructor applying a learned gradient descent iterative scheme.

Note that the weights are not shared across the blocks, like presented in the original paper 1. This implementation rather follows https://github.com/adler-j/learned_primal_dual/blob/master/ellipses/learned_primal.py.

References

1

Jonas Adler & Ozan Öktem (2017). Solving ill-posed inverse problems using iterative deep neural networks. Inverse Problems, 33(12), 124007.

HYPER_PARAMS = {'batch_norm': {'default': False, 'retrain': True}, 'batch_size': {'default': 32, 'retrain': True}, 'epochs': {'default': 20, 'retrain': True}, 'init_fbp': {'default': True, 'retrain': True}, 'init_filter_type': {'default': 'Hann', 'retrain': True}, 'init_frequency_scaling': {'default': 0.4, 'retrain': True}, 'init_weight_gain': {'default': 1.0, 'retrain': True}, 'init_weight_xavier_normal': {'default': False, 'retrain': True}, 'internal_ch': {'default': 32, 'retrain': True}, 'kernel_size': {'default': 3, 'retrain': True}, 'lr': {'default': 0.01, 'retrain': True}, 'lr_time_decay_rate': {'default': 3.2, 'retrain': True}, 'lrelu_coeff': {'default': 0.2, 'retrain': True}, 'niter': {'default': 5, 'retrain': True}, 'nlayer': {'default': 3, 'retrain': True}, 'normalize_by_opnorm': {'default': True, 'retrain': True}, 'prelu': {'default': False, '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().

property batch_norm

property batch_size

property epochs

property init_fbp

property init_filter_type

property init_frequency_scaling

property init_weight_gain

property init_weight_xavier_normal

property internal_ch

property kernel_size

property lr

property lr_time_decay_rate

property lrelu_coeff

property niter

property nlayer

property normalize_by_opnorm

property prelu

property use_sigmoid