TemporalMLP

class daart.models.temporalmlp.TemporalMLP(hparams, type='encoder', in_size=None, hid_size=None, out_size=None)

Bases: BaseModel

MLP network with initial 1D convolution layer.

Methods Summary

build_decoder(in_size, hid_size, out_size)	Construct the vanilla MLP decoder using hparams.
build_encoder(in_size, hid_size, out_size)	Construct the encoder using hparams.
forward(x, **kwargs)	Process input data.

Methods Documentation

build_decoder(in_size, hid_size, out_size)

Construct the vanilla MLP decoder using hparams.

build_encoder(in_size, hid_size, out_size)

Construct the encoder using hparams.

forward(x, **kwargs)

Process input data.

Parameters:

x (torch.Tensor object) – input data of shape (n_sequences, sequence_length, n_markers)

Returns:

shape (n_sequences, sequence_length, n) where n is the embedding dimension if an encoder, or n_markers if a decoder/predictor

Return type:

torch.Tensor