We will start by specifying a few things that we will need for the training process. Let's take a look at the following code:
# Initial settings
b <- 50
setwd("~/Desktop/")
dir <- "FakeImages"
dir.create(dir)
start <- 1; dloss <- NULL; gloss <- NULL
From the preceding code, we can observe the following:
- We will use a batch size (b) of 50.
- We will save fake images in the FakeImages directory, which is created on the desktop of our computer.
- We will also make use of discriminator loss values (dloss) and GAN loss values (gloss), which are initialized with NULL.