pyprobound.layers.roll.RollSpec

class RollSpec(alphabet, direction, max_length=None, include_n=False, name='')

Bases: LayerSpec

Specification for changing between left, right, and center padding.

__init__(alphabet, direction, max_length=None, include_n=False, name='')

Initializes the rolling specification.

Parameters:

• alphabet (Alphabet) – The alphabet used to encode sequences into tensors.

• direction (Literal['left', 'right', 'center']) – Whether to justify the ends of sequences on the left, right, or center.

• max_length (int | None) – The number of elements to keep from the aligned end. Ex. […,:max_length] if left, […,-max_length:] if right.

• include_n (bool) – Whether to use the * character as a padding value.

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

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.
max_length	The number of elements to keep from the aligned end.
out_channels	The number of output channels.
unfreezable	alias of Literal['all']

Non-Inherited Members

property max_length: int | None

The number of elements to keep from the aligned end.

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.