niftynet.network.toynet module

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

Bases: niftynet.network.base_net.BaseNet

### Description
Toy net for testing

### Diagram INPUT –> CONV(kernel = 3, activation = relu) –> CONV(kernel = 1, activation = None) –> MULTICLASS OUTPUT

### Constraints None

__init__(num_classes, w_initializer=None, w_regularizer=None, b_initializer=None, b_regularizer=None, acti_func='prelu', name='ToyNet')[source]
Parameters:
  • num_classes – int, number of final output channels
  • 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 – ctivation function to use
  • name – layer name
layer_op(images, is_training=True, **unused_kwargs)[source]
Parameters:
  • images – tensor, input to the network
  • is_training – boolean, True if network is in training mode
  • unused_kwargs – other arguments, not in use
Returns:

tensor, network output