VesselFillingNetwork

This module implements the vessel filling neuronal network in PyTorch.

class DeSepConv3d(nin, nout)

Bases: torch.nn.modules.module.Module

Depthwise separable convolutional layer.

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class VesselFillingNetwork(load=None)

Bases: torch.nn.modules.module.Module

Vessel filling neuronal network.

decode(x)

encode(inp)

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.