niftynet.network.holistic_net module¶

class HolisticNet(num_classes, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='elu', name='HolisticNet')[source]¶

Bases: niftynet.network.base_net.BaseNet

Implementation of HolisticNet detailed in Fidon, L. et. al. (2017) Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks. MICCAI 2017 (BrainLes)

layer_op(input_tensor, is_training=True, layer_id=-1, **unused_kwargs)[source]¶

class ScoreLayer(num_features=None, w_initializer=None, w_regularizer=None, num_classes=1, acti_func='elu', name='ScoreLayer')[source]¶

Bases: niftynet.layer.base_layer.TrainableLayer

layer_op(input_tensor, is_training, layer_id=-1)[source]¶

class MergeLayer(func, w_initializer=None, w_regularizer=None, acti_func='elu', name='MergeLayer')[source]¶

Bases: niftynet.layer.base_layer.TrainableLayer

layer_op(roots)[source]¶