terminator.models.layers.condense.ContactIndexEncoding

class terminator.models.layers.condense.ContactIndexEncoding(hparams)[source]

Bases: Module

Module which sinusoidally embeds contact indices

Variables:

  • dropout (nn.Dropout) – Dropout module

  • cie_scaling (int) – Multiplicative scaling factor for inputted contact indices

  • cie_offset (int) – Additive scaling factor for inputted contact indices

__init__(hparams)[source]
Parameters:

hparams (dict) – Dictionary of model hparams (see ~/scripts/models/train/default_hparams.json for more info)

Methods

__init__(hparams)

Parameters:

hparams (dict) -- Dictionary of model hparams (see ~/scripts/models/train/default_hparams.json for more info)

forward(contact_idxs[, mask])

Embed contact indicies sinusoidally

Attributes

T_destination

alias of TypeVar('T_destination', bound=Mapping[str, Tensor])

dump_patches

This allows better BC support for load_state_dict().
forward(contact_idxs, mask=None)[source]

Embed contact indicies sinusoidally

Parameters:

contact_idxs (torch.LongTensor) – Contact indices

Returns:

cie – Sinusoidally embedded contact indices

Return type:

torch.Tensor