niftynet.network.scalenet module

class niftynet.network.scalenet.ScaleBlock(func, n_layers=1, w_initializer=None, w_regularizer=None, acti_func='relu', name='scaleblock')

Bases: niftynet.layer.base_layer.TrainableLayer

layer_op(input_tensor, is_training)

class niftynet.network.scalenet.ScaleNet(num_classes, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='prelu', name='ScaleNet')

Bases: niftynet.network.base_net.BaseNet

implementation of ScaleNet:

Fidon et al., “Scalable multimodal convolutional networks for brain tumour segmentation”, MICCAI ‘17

layer_op(images, is_training, layer_id=-1)