Composite Layers#

Classes#

class Branch(net_check, branches, shapes, *, checkpoint=True, dim=0, channels=None, root='', method='concat', shape=None, defaults=None, **kwargs)[source]

Bases: BaseLayer

Creates a branching layer that processes the input through multiple branches and combines the outputs.

Attributes:

groupint: Layer group, if 0 it will always be used, else it will only be used if its group matches the Networks
descriptionstr: Description of the layer
brancheslist[BaseLayer]: List of subnetworks for each branch
headConcatenate | Pack | Shortcut: Layer to combine the outputs from each branch, either concatenation, packing or summation

Parameters:

net_checkbool: If layer index should be relative to checkpoint layers
brancheslist[list[dict[str, Any]]]: List of layer configurations for each branch
shapesShapes: Shape of the outputs from each layer
checkpointbool, Optional: If layer index should be relative to checkpoint layers, default = True
dimint, Optional: Dimension to concatenate along if method is ‘concat’, default = 0
channelsint, Optional: Number of output channels, won’t be used if shape is provided, if channels and shape aren’t provided, the input dimensions will be preserved
rootstr, Optional: Root directory to prepend to config file path
methodLiteral[‘concat’, ‘pack’, ‘sum’], Optional: Method to combine the outputs from each branch, either concatenation, packing or summation, default = ‘concat’
shapelist[int] | NoneType, Optional: Output shape of the block, will be used if provided; otherwise, channels will be used
defaultsdict[str, Any] | NoneType, Optional: Default values for the parameters for each type of layer
**kwargs: Leftover parameters to pass to base layer for checking

extra_repr()[source]

Displays layer parameters when printing the network.

Returns:

str: Layer parameters

forward(x, *_, **__)[source]

Forward pass for the Branch layer.

Parameters:

xTensorListT: Input tensor(s) with dtype float32 and shape (N,…), where N is batch size

Returns:

TensorListT: Output tensor(s) from the subnetwork with dtype float32 and shape (N,…)

to(*args, **kwargs)[source]: See torch.nn.Module.to().

class Composite(net_check, name, shapes, *, checkpoint=True, channels=None, root='', config_dir='', shape=None, defaults=None, config=None, **kwargs)[source]

Bases: BaseLayer

Creates a subnetwork from a configuration file.

Attributes:

groupint: Layer group, if 0 it will always be used, else it will only be used if its group matches the Networks
descriptionstr: Description of the layer
netNetwork: Subnetwork for the Composite layer

Parameters:

net_checkbool: If layer index should be relative to checkpoint layers
namestr: Name of the subnetwork
shapesShapes: Shape of the outputs from each layer
checkpointbool, Optional: If layer index should be relative to checkpoint layers, default = True
channelsint, Optional: Number of output channels, won’t be used if shape is provided, if channels and shape aren’t provided, the input dimensions will be preserved
rootstr, Optional: Root directory to prepend to config file path
config_dirstr, Optional: Path to the directory with the network configuration file, won’t be used if config is provided
shapelist[int] | NoneType, Optional: Output shape of the block, will be used if provided; otherwise, channels will be used
defaultsdict[str, Any] | NoneType, Optional: Default values for the parameters for each type of layer
configdict[str, Any] | Config | NoneType, Optional: Network configuration dictionary
**kwargs: Leftover parameters to pass to base layer for checking

extra_repr()[source]

Displays layer parameters when printing the network.

Returns:

str: Layer parameters

forward(x, *_, **__)[source]

Forward pass for the Composite layer.

Parameters:

xTensorListT: Input tensor(s) with dtype float32 and shape (N,…), where N is batch size

Returns:

TensorListT: Output tensor(s) from the subnetwork with dtype float32 and shape (N,…)

to(*args, **kwargs)[source]: See torch.nn.Module.to().