layer_wavenet_dilated_causal_convolution_1d: Wavenet residual connections

In r-tensorflow/wavenet: WaveNet: A Generative Model for Raw Audio

Description

Residual connection as described in section 2.3 of van den Oord et al., WaveNet: A Generative Model for Raw Audio.

Usage

layer_wavenet_dilated_causal_convolution_1d(object, filters, kernel_size,
  dilation_rate, name = NULL, trainable = TRUE)

Arguments

object	Model or layer object
filters	Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution).
kernel_size	An integer or list of a single integer, specifying the length of the 1D convolution window.
dilation_rate	an integer or list of a single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any dilation_rate value != 1 is incompatible with specifying any strides value != 1.
name	An optional name string for the layer. Should be unique in a model (do not reuse the same name twice). It will be autogenerated if it isn't provided.
trainable	Whether the layer weights will be updated during training.

r-tensorflow/wavenet documentation built on Nov. 5, 2019, 2:06 a.m.