def load_mnist(path=".", normalize=True):
mnist_dataset = MNIST(path=path, normalize=normalize)
return mnist_dataset.load_data()
from neon.util.argparser import NeonArgparser
# parse the command line arguments
parser = NeonArgparser(__doc__)
parser.add_argument('--kbatch',
type=int,
default=1,
help='number of data batches per noise batch in training')
parser.add_argument(
"--original_cost",
action='store_true',
help="generator cost log(1-D(G(z))) rather than -log(D(G(z)))")
args = parser.parse_args()
# load up the mnist data set
dataset = MNIST(path=args.data_dir, size=27)
train_set = dataset.train_iter
valid_set = dataset.valid_iter
# setup weight initialization function
init = Gaussian(scale=0.05)
# generator using "decovolution" layers
relu = Rectlin(slope=0) # relu for generator
conv = dict(init=init, batch_norm=True, activation=relu)
convp1 = dict(init=init, batch_norm=True, activation=relu, padding=1)
convp2 = dict(init=init, batch_norm=True, activation=relu, padding=2)
convp1s2 = dict(init=init,
batch_norm=True,
activation=relu,
padding=1,
from neon.util.persist import ensure_dirs_exist
# parse the command line arguments
parser = NeonArgparser(__doc__)
parser.add_argument('--kbatch',
type=int,
default=1,
help='number of data batches per noise batch in training')
parser.add_argument('--subset_pct',
type=float,
default=100,
help='subset percentage of training dataset to use')
args = parser.parse_args()
# load up the mnist data set
dataset = MNIST(path=args.data_dir, subset_pct=args.subset_pct, size=27)
train_set = dataset.train_iter
valid_set = dataset.valid_iter
# setup weight initialization function
init = Gaussian(scale=0.05)
# generator using "decovolution" layers
relu = Rectlin(slope=0) # relu for generator
conv = dict(init=init, batch_norm=True, activation=relu)
convp1 = dict(init=init, batch_norm=True, activation=relu, padding=1)
convp2 = dict(init=init, batch_norm=True, activation=relu, padding=2)
convp1s2 = dict(init=init,
batch_norm=True,
activation=relu,
padding=1,
type=str,
default='dc',
help='generator model type: dc or mlp, default dc')
parser.add_argument('--n_dis_ftr',
type=int,
default=64,
help='base discriminator feature number, default 64')
parser.add_argument('--n_gen_ftr',
type=int,
default=64,
help='base generator feature number, default 64')
args = parser.parse_args()
random_seed = args.rng_seed if args.rng_seed else 0
# load up the mnist data set, padding images to size 32
dataset = MNIST(path=args.data_dir, sym_range=True, size=32, shuffle=True)
train = dataset.train_iter
# create a GAN
model, cost = create_model(dis_model=args.dmodel,
gen_model=args.gmodel,
cost_type='wasserstein',
noise_type='normal',
im_size=32,
n_chan=1,
n_noise=128,
n_gen_ftr=args.n_gen_ftr,
n_dis_ftr=args.n_dis_ftr,
depth=4,
n_extra_layers=4,
batch_norm=True,
def load_mnist(path=".", normalize=True):
mnist_dataset = MNIST(path=path, normalize=normalize)
return mnist_dataset.load_data()