pyprobound.layers.conv0d.Conv0d

class Conv0d(nonspecific, input_shape, min_input_length, max_input_length, train_posbias=False)

Bases: Layer

Non-specific ‘0D convolution’ with length biases.

Flattens the length dimension into a single value proportional to the number of finite elements in each sequence in log space.

log_posbias

The bias for each input length \(\omega(|S_i|)\).

Type:: Tensor

__init__(nonspecific, input_shape, min_input_length, max_input_length, train_posbias=False)

Initializes the 0d convolution layer.

Parameters:

nonspecific (NonSpecific) – The specification of the 0d convolution 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.
train_posbias (bool) – Whether to train a bias for each input length.

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)	Calculates the log score of each sequence.
`freeze`()	Turns off gradient calculation for all parameters.
`from_nonspecific`(nonspecific, prev[, ...])	Creates a new instance from a specification and an input component.
`get_log_posbias`()	The bias for each input length \(\omega(\|S_i\|)\).
`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', 'posbias']

Non-Inherited Members

unfreezable: alias of Literal[‘all’, ‘posbias’]

classmethod from_nonspecific(nonspecific, prev, train_posbias=False)

Creates a new instance from a specification and an input component.

Parameters:

spec – The specification of the 0d convolution layer.
prev (Union[Table[Any], Layer]) – If used as the first layer, the table that will be passed as an input; otherwise, the layer that precedes it.
train_posbias (bool) – Whether to train a bias for each input length.

Return type:

Self

max_embedding_size()

The maximum number of bytes needed to encode a sequence.

Used for splitting calculations to avoid GPU limits on tensor sizes.

Return type:: int

check_length_consistency()

Checks that input lengths of Binding components are consistent.

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

unfreeze(parameter='all')

Turns on gradient calculation for the specified parameter.

Parameters:: parameter (Literal['all', 'posbias']) – Parameter to be unfrozen, defaults to all parameters.
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

get_log_posbias()

The bias for each input length \(\omega(|S_i|)\).

Return type:: Tensor
Returns:: A tensor with the bias of each input length of shape \((\text{input_lengths},1,1)\).

forward(seqs)

Calculates the log score of each sequence.

\[\log \omega(|S_i|) + |S_i|\]

Parameters:: seqs (Tensor) – A sequence tensor of shape \((\text{minibatch},\text{length})\) or \((\text{minibatch},\text{in_channels},\text{length})\).
Return type:: Tensor
Returns:: The log score tensor of shape \((\text{minibatch},1,1)\).