terminator.models.layers.s2s_modules.NodeTransformerLayer

class terminator.models.layers.s2s_modules.NodeTransformerLayer(num_hidden, num_in, num_heads=4, dropout=0.1)

Bases: Module

__init__(num_hidden, num_in, num_heads=4, dropout=0.1)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__(num_hidden, num_in[, num_heads, ...])	Initializes internal Module state, shared by both nn.Module and ScriptModule.
forward(h_V, h_E[, mask_V, mask_attend])	Parallel computation of full transformer layer
step(t, h_V, h_E[, mask_V, mask_attend])	Sequential computation of step t of a transformer layer

Attributes

T_destination	alias of TypeVar('T_destination', bound=Mapping[str, Tensor])
dump_patches	This allows better BC support for load_state_dict().

forward(h_V, h_E, mask_V=None, mask_attend=None)

Parallel computation of full transformer layer

step(t, h_V, h_E, mask_V=None, mask_attend=None)

Sequential computation of step t of a transformer layer