pyprobound.layers.layer.Layer

class Layer(layer_spec, input_shape, min_input_length, max_input_length, name='')

Bases: Transform, LengthManager

Experiment-specific LayerSpec container.

layer_spec

The specification of the layer.

Type:: LayerSpec

_modes

Tuples of every binding mode and respective index that a layer appears in.

Type:: set[tuple[Mode, int]]

__init__(layer_spec, input_shape, min_input_length, max_input_length, name='')

Initializes the layer.

Parameters:

layer_spec (LayerSpec) – The specification of the layer.
input_shape (int) – The number of elements in an input sequence.
min_input_length (int) – The minimum number of finite elements in an input sequence.
max_input_length (int) – The maximum number of finite elements in an input sequence.
name (str) – A string used to describe the layer.

Methods

`cache`(fun)	Decorator for a function to cache its output.
`check_length_consistency`()	Checks that input lengths of Binding components are consistent.
`components`()	Iterator of child components.
`forward`(seqs)	A transformation applied to a sequence tensor.
`freeze`()	Turns off gradient calculation for all parameters.
`in_len`(length[, mode])	Calculates the receptive field.
`lengths`(seqs)	Counts the number of finite elements in each sequence.
`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.
`update_input_length`([left_shift, ...])	Updates input shapes, called by a child LayerSpec after its update.

Attributes

`in_channels`	The number of input channels.
`input_shape`	The number of elements in an input sequence.
`max_input_length`	The maximum number of finite elements in an input sequence.
`min_input_length`	The minimum number of finite elements in an input sequence.
`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.

property input_shape: int: The number of elements in an input sequence.

property min_input_length: int: The minimum number of finite elements in an input sequence.

property max_input_length: int: The maximum number of finite elements in an input sequence.

out_len(length, mode='shape')

Calculates the number of elements in the output length dimension.

Parameters:

length (TypeVar(T, int, Tensor)) – The input length.
mode (Literal['min', 'max', 'shape']) – Either shape, which returns the number of elements, or min or max, which return the minimum or maximum number of finite elements.

Return type:

TypeVar(T, int, Tensor)

Returns:

The number of elements in the output length dimension, according to the specified mode.

in_len(length, mode='max')

Calculates the receptive field.

Parameters:

length (TypeVar(T, int, Tensor)) – The output length.
mode (Literal['min', 'max']) – Either min or max, representing the minimum or maximum number of positions contributing to the output length.

Return type:

Optional[TypeVar(T, int, Tensor)]

Returns:

The number of input positions that contribute to the values of the corresponding number of output positions. Outputs None if the max receptive field is undefined.

components()

Iterator of child components.

Return type:: Iterator[Component]

check_length_consistency()

Checks that input lengths of Binding components are consistent.

Raises:: RuntimeError – There is an input mismatch between components.
Return type:: None

update_binding_optim(binding_optim)

Updates a BindingOptim with the specification’s optimization steps.

Parameters:: binding_optim (BindingOptim) – The parent BindingOptim to be updated.
Return type:: BindingOptim
Returns:: The updated BindingOptim.

update_input_length(left_shift=0, right_shift=0, min_len_shift=0, max_len_shift=0, new_min_len=None, new_max_len=None)

Updates input shapes, called by a child LayerSpec after its update.

Parameters:

left_shift (int) – The change in size on the left side of the sequence.
right_shift (int) – The change in size on the right side of the sequence.
min_len_shift (int) – The change in the number of short input lengths.
max_len_shift (int) – The change in the number of long input lengths.
new_min_len (int | None) – The new min_input_length.
new_max_len (int | None) – The new max_input_length.

Return type:

None

lengths(seqs)

Counts the number of finite elements in each sequence.

Parameters:: seqs (Tensor) – A sequence tensor of shape \((\text{minibatch},\text{length})\) or \((\text{minibatch},\text{in_channels},\text{in_length})\).
Return type:: Tensor
Returns:: A tensor with the number of finite elements in each sequence of shape \((\text{minibatch},)\).