Conv_tbc

Usage

torch_conv_tbc(self, weight, bias, pad = 0L)

Arguments

self

NA input tensor of shape $(\text{sequence length}\times batch\times \text{in\_channels})$

weight

NA filter of shape ($\text{kernel width}\times \text{in\_channels}\times \text{out\_channels}$)

bias

NA bias of shape ($\text{out\_channels}$)

pad

NA number of timesteps to pad. Default: 0

TEST

Applies a 1-dimensional sequence convolution over an input sequence. Input and output dimensions are (Time, Batch, Channels) - hence TBC.