Conventions used

There are a number of text conventions used throughout this book.

Code in text: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles. Here is an example: "And because batch_size is now coupled with world_size, we provide it as an input argument for an easier training interface."

A block of code is set as follows:

# define the optimization schedule for both G and D
opt_gen = torch.optim.Adam(gen.parameters(), lr=lrate)
opt_disc = torch.optim.Adam(disc.parameters(), lr=lrate)

When we wish to draw your attention to a particular part of a code block, the relevant lines or items are set in bold:

def main():
    parser.add_argument('--num-gpu-processes', default=1, type=int)
    args.world_size = args.num_gpu_processes * args.num_machines                
    mp.spawn(train, nprocs=args.num_gpu_processes, args=(args,))

Any command-line input or output is written as follows:

jupyter==1.0.0
torch==1.4.0
torchvision==0.5.0 matplotlib==3.1.2
pytorch-lightning==1.0.5
fastai==2.1.8

Bold: Indicates a new term, an important word, or words that you see onscreen. For example, words in menus or dialog boxes appear in the text like this. Here is an example: "First, the random noise input vector of size 64 is reshaped and projected into 128 feature maps of size 16x16 each."

Tips or important notes

Appear like this.