Generator {RGAN}

Generator

Description

Provides a torch::nn_module with a simple fully connected neural net, for use as the default architecture for tabular data in RGAN.

Usage

Generator(
  noise_dim,
  data_dim,
  hidden_units = list(128, 128),
  dropout_rate = 0.5
)

Arguments

noise_dim

The length of the noise vector per example

data_dim

The number of columns in the data set

hidden_units

A list of the number of neurons per layer, the length of the list determines the number of hidden layers

dropout_rate

The dropout rate for each hidden layer

Value

A torch::nn_module for the Generator