niftynet.contrib.csv_reader.highres3dnet_features module

class HighRes3DNetFeatures(w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='prelu', name='HighRes3DNet')

Bases: niftynet.network.base_net.BaseNet

implementation of HighRes3DNet:

Li et al., “On the compactness, efficiency, and representation of 3D convolutional networks: Brain parcellation as a pretext task”, IPMI ‘17

layer_op(images, is_training, layer_id=-1)

class HighResBlock(n_output_chns, kernels=(3, 3), acti_func='relu', w_initializer=None, w_regularizer=None, with_res=True, name='HighResBlock')

Bases: niftynet.layer.base_layer.TrainableLayer

This class define a high-resolution block with residual connections kernels

• specify kernel sizes of each convolutional layer
• e.g.: kernels=(5, 5, 5) indicate three conv layers of kernel_size 5

with_res

• whether to add residual connections to bypass the conv layers

layer_op(input_tensor, is_training)