Multilevelnet

Auto-generated documentation for labelprop.MultiLevelNet module.

MultiLevelNet

Convolutional network generating deformation field with different scales.

class MultiLevelNet(nn.Module):
    def __init__(self, inshape, in_channels=2, levels=3, features=16): ...

For each levels, downsample the input and apply the convolutional block.

def forward(self, x, registration=False): ...

For each levels, create a convolutional block with two Conv Tanh BatchNorm layers

def get_conv_blocks(self, in_channels, levels, intermediate_features): ...

def get_downsample_blocks(self, in_channels, levels): ...