core.nn.enets.ModuleMerger

core.nn.enets.ModuleMerger(module_list)

This is a wrapper used to process multiple different kinds of context information collected in x = (x_0, x_1, …). For each kind of context information x_i, an individual embedding network is provided in enets = (enet_0, enet_1, …). The embedded output of the forward method is the concatenation of the individual embeddings enet_i(x_i).

In the GW use case, this wrapper can be used to embed the high-dimensional signal input into a lower dimensional feature vector with a large embedding network, while applying an identity embedding to the time shifts.

Module specs

input dimension:    (batch_size, ...), (batch_size, ...), ...
output dimension:   (batch_size, ?)

Parameters

Name Type Description Default
module_list tuple nn.Modules for embedding networks, use torch.nn.Identity for identity mappings required

Attributes

Name Description
enets

Methods

Name Description
forward

forward

core.nn.enets.ModuleMerger.forward(*x)