niftynet.network.holistic_net module¶
-
class
niftynet.network.holistic_net.HolisticNet(num_classes, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='elu', name='HolisticNet')¶ Bases:
niftynet.network.base_net.BaseNetImplementation 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, layer_id=-1)¶
-
-
class
niftynet.network.holistic_net.MergeLayer(func, w_initializer=None, w_regularizer=None, acti_func='elu', name='MergeLayer')¶ Bases:
niftynet.layer.base_layer.TrainableLayer-
layer_op(roots)¶
-
-
class
niftynet.network.holistic_net.ScoreLayer(num_features=None, w_initializer=None, w_regularizer=None, num_classes=1, acti_func='elu', name='ScoreLayer')¶ Bases:
niftynet.layer.base_layer.TrainableLayer-
layer_op(input_tensor, is_training, layer_id=-1)¶
-
