main.py

import argparse, os
from GAN import GAN
from CGAN import CGAN
from WGAN import WGAN
from VAE import VAE
from LSGAN import LSGAN
from CVAE import CVAE
from WGAN_GP import WGAN_GP
from EBGAN import EBGAN
from infoGAN import infoGAN
from ACGAN import ACGAN
from SAGAN import SAGAN

"""parsing and configuration"""
def parse_args():
    desc = "Pytorch implementation of GAN collections"
    parser = argparse.ArgumentParser(description=desc)

    parser.add_argument('--gan_type', type=str, default='EBGAN',
                        choices=['GAN', 'CGAN','VAE', 'infoGAN', 'ACGAN', 'EBGAN', 'BEGAN', 'WGAN', 'WGAN_GP',
                                 'DRAGAN', 'LSGAN', 'CVAE', 'SAGAN'],
                        help='The type of GAN')#, required=True)
    parser.add_argument('--dataset', type=str, default='mnist', choices=['mnist', 'fashion-mnist', 'celebA'],
                        help='The name of dataset')
    parser.add_argument('--epoch', type=int, default=25, help='The number of epochs to run')
    parser.add_argument('--batch_size', type=int, default=64, help='The size of batch')
    parser.add_argument('--save_dir', type=str, default='models',
                        help='Directory name to save the model')
    parser.add_argument('--result_dir', type=str, default='results',
                        help='Directory name to save the generated images')
    parser.add_argument('--log_dir', type=str, default='logs',
                        help='Directory name to save training logs')
    parser.add_argument('--lrG', type=float, default=0.0002)
    parser.add_argument('--lrD', type=float, default=0.0002)
    parser.add_argument('--beta1', type=float, default=0.5)
    parser.add_argument('--beta2', type=float, default=0.999)
    parser.add_argument('--gpu_mode', type=bool, default=True)

    return check_args(parser.parse_args())

"""checking arguments"""
def check_args(args):
    # --save_dir
    if not os.path.exists(args.save_dir):
        os.makedirs(args.save_dir)

    # --result_dir
    if not os.path.exists(args.result_dir):
        os.makedirs(args.result_dir)

    # --result_dir
    if not os.path.exists(args.log_dir):
        os.makedirs(args.log_dir)

    # --epoch
    try:
        assert args.epoch >= 1
    except:
        print('number of epochs must be larger than or equal to one')

    # --batch_size
    try:
        assert args.batch_size >= 1
    except:
        print('batch size must be larger than or equal to one')

    return args


"""main"""
def main():
    # parse arguments
    args = parse_args()
    if args is None:
        exit()

        # declare instance for GAN
    if args.gan_type == 'GAN':
        gan = GAN(args)
    elif args.gan_type == 'CGAN':
        gan = CGAN(args)
    elif args.gan_type == 'WGAN':
        gan = WGAN(args)
    elif args.gan_type == 'VAE':
        gan = VAE(args)
    elif args.gan_type == 'LSGAN':
        gan = LSGAN(args)
    elif args.gan_type == 'CVAE':
        gan = CVAE(args)
    elif args.gan_type == 'WGAN_GP':
        gan = WGAN_GP(args)
    elif args.gan_type == 'LSGAN':
        gan = LSGAN(args)
    elif args.gan_type == 'EBGAN':
        gan = EBGAN(args)
    elif args.gan_type == 'infoGAN':
        gan = infoGAN(args)
    elif args.gan_type == 'ACGAN':
        gan = ACGAN(args)
    elif args.gan_type == 'SAGAN':
        gan = SAGAN(args)
    else:
        raise Exception("[!] There is no option for " + args.gan_type)

        # launch the graph in a session
    gan.train()
    print(" [*] Training finished!")

    # visualize learned generator
    gan.visualize_results(args.epoch)
    print(" [*] Testing finished!")


if __name__ == '__main__':
    main()