wavenet: Builds the WaveNet model

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

Description

Builds the WaveNet model as described in van den Oord et al., WaveNet: A Generative Model for Raw Audio.

Usage

wavenet(filters = 16, kernel_size = 2, residual_blocks,
  input_shape = list(NULL, 1), input_tensor = NULL,
  initial_kernel_size = 32, initial_filters = 32,
  output_channels = 256, output_activation = "softmax")

Arguments

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.
residual_blocks	if a single integer: the number of residual blocks in the model - the dilation rate of each block 'i' is calculated by '2^i'. If a vector, then it's used as the dilation rate of each residual block.
input_shape	input shape for the model (not including the axis dimension). Typically length 2 numeric vector. Used to build the 'input_tensor' if no 'input_tensor' is specified.
input_tensor	Tensor to use as input for the model. Usually a 3d tensor.
initial_kernel_size	kernel size of the first causal convolution.
initial_filters	number of filters in the initial causal convolution.
output_channels	number of channels in the output.
output_activation	activation function for the last layer. Default: 'softmax'

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