DCGAN_Discriminator

The number of channels in the image (RGB is 3 channels)

number_channels

The number of feature maps in discriminator

The dropout rate for each hidden layer

dropout_rate

Switch between a sigmoid and linear output layer (the sigmoid is needed for the original GAN value function)

sigmoid

Provides a torch::nn_module with a simple deep convolutional neural
net architecture, for use as the default architecture for image data in RGAN.
Architecture inspired by: <a href="https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html">https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html</a>

An easy way to get started with Generative Adversarial Nets (GAN) in R. The GAN algorithm was initially
described by Goodfellow et al. 2014 <https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf>. A GAN can be used to learn the joint distribution of complex data by
comparison. A GAN consists of two neural networks a Generator and a Discriminator, where the two
neural networks play an adversarial minimax game.
Built-in GAN models make the training of GANs in R possible in one line and make it easy to
experiment with different design choices (e.g. different network architectures, value functions, optimizers).
The built-in GAN models work with tabular data (e.g. to produce synthetic data) and image data.
Methods to post-process the output of GAN models to enhance the quality of samples are available.

Marcel Neunhoeffer

RGAN

Generative Adversarial Nets (GAN) in R

DCGAN_Discriminator function

Provides a torch::nn_module with a simple deep convolutional neural
net architecture, for use as the default architecture for image data in RGAN.
Architecture inspired by: <a href='https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html'>https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html</a>

DCGAN_Discriminator: DCGAN Discriminator

Description

Usage

Arguments

Value