niftynet.network.highres3dnet_small module

class HighRes3DNetSmall(num_classes, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='relu', name='HighRes3DNetSmall')[source]

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

(This is smaller model with an initial stride-2 convolution)

### Constraints - Input image size should be divisible by 8

__init__(num_classes, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='relu', name='HighRes3DNetSmall')[source]
Parameters:
  • num_classes – int, number of channels of output
  • w_initializer – weight initialisation for network
  • w_regularizer – weight regularisation for network
  • b_initializer – bias initialisation for network
  • b_regularizer – bias regularisation for network
  • acti_func – activation function to use
  • name – layer name
layer_op(images, is_training=True, layer_id=-1, **unused_kwargs)[source]
Parameters:
  • images – tensor to input to the network. Size has to be divisible by 8
  • is_training – boolean, True if network is in training mode
  • layer_id – int, index of the layer to return as output
  • unused_kwargs
Returns:

output of layer indicated by layer_id