niftynet.layer.upsample module¶
-
class
UpSampleLayer
(func, kernel_size=3, stride=2, w_initializer=None, w_regularizer=None, with_bias=False, b_initializer=None, b_regularizer=None, name='upsample')[source]¶ Bases:
niftynet.layer.base_layer.TrainableLayer
This class defines channel-wise upsampling operations. Different from
DeconvLayer
, the elements are not mixed in the channel dim.REPLICATE
mode replicates each spatial_dim intospatial_dim*kernel_size
CHANNELWISE_DECONV` mode makes a projection using a kernel. e.g., With 2D input (without loss of generality), given input[N, X, Y, C]
, the output is[N, X*kernel_size, Y*kernel_size, C]
.