pyprobound.layers.layer.LayerSpec

class LayerSpec(out_channels, in_channels, name='')

Bases: Spec, LengthManager

A component that stores experiment-independent parameters of layers.

The forward implementation should be left to the Layer.

_layers

All of the layers a specification appears in.

Type:

set[Layer]

__init__(out_channels, in_channels, name='')

Initializes the layer specification.

Parameters:

• out_channels (int) – The number of output channels.

• in_channels (int) – The number of input channels.

• name (str) – A string used to describe the layer.

Methods

check_length_consistency()	Checks that input lengths of Binding components are consistent.
components()	Iterator of child components.
forward()	Define the computation performed at every call.
freeze()	Turns off gradient calculation for all parameters.
in_len(length[, mode])	Calculates the receptive field.
max_embedding_size()	The maximum number of bytes needed to encode a sequence.
optim_procedure([ancestry, current_order])	The sequential optimization procedure for all Binding components.
out_len(length[, mode])	Calculates the number of elements in the output length dimension.
reload(checkpoint)	Loads the model from a checkpoint file.
reload_from_state_dict(state_dict)	Loads the model from a state dict.
save(checkpoint[, flank_lengths])	Saves the model to a file with "state_dict" and "metadata" fields.
unfreeze([parameter])	Turns on gradient calculation for the specified parameter.
update_binding_optim(binding_optim)	Updates a BindingOptim with the specification's optimization steps.

Attributes

in_channels	The number of input channels.
out_channels	The number of output channels.
unfreezable	alias of Literal['all']

Non-Inherited Members

property out_channels: int

The number of output channels.

property in_channels: int

The number of input channels.

components()

Iterator of child components.

Return type:

Iterator[Component]