niftynet.layer.residual_unit module¶
-
class
ResidualUnit
(n_output_chns=1, kernel_size=3, dilation=1, acti_func='relu', w_initializer=None, w_regularizer=None, moving_decay=0.9, eps=1e-05, type_string='bn_acti_conv', name='res-downsample')[source]¶ Bases:
niftynet.layer.base_layer.TrainableLayer
-
__init__
(n_output_chns=1, kernel_size=3, dilation=1, acti_func='relu', w_initializer=None, w_regularizer=None, moving_decay=0.9, eps=1e-05, type_string='bn_acti_conv', name='res-downsample')[source]¶ Implementation of residual unit presented in:
[1] He et al., Identity mapping in deep residual networks, ECCV 2016 [2] He et al., Deep residual learning for image recognition, CVPR 2016The possible types of connections are:
'original': residual unit presented in [2] 'conv_bn_acti': ReLU before addition presented in [1] 'acti_conv_bn': ReLU-only pre-activation presented in [1] 'bn_acti_conv': full pre-activation presented in [1]
[1] recommends ‘bn_acti_conv’
Parameters: - n_output_chns – number of output feature channels if this doesn’t match the input, a 1x1 projection will be created.
- kernel_size –
- dilation –
- acti_func –
- w_initializer –
- w_regularizer –
- moving_decay –
- eps –
- type_string –
- name –
-