default=100,
metavar='N',
help='number of samples for importance sampling (default: 10)')
parser.add_argument('--model',
type=str,
default="",
metavar='N',
help='save model checkpoint')
parser.add_argument('--alpha',
type=float,
default=1.,
metavar='N',
help='set value of alpha')
args = parser.parse_args()
train_loader = torch.utils.data.DataLoader(MNISTBinarized(
'../dataset/mnist', train=True, download=True),
batch_size=args.batch_size,
shuffle=True,
num_workers=0)
test_loader = torch.utils.data.DataLoader(MNISTBinarized(
'../dataset/mnist', train=False),
batch_size=args.batch_size,
shuffle=False,
num_workers=0)
gmmae = GMMVAE(input_dim=784,
z_dim=20,
n_components=10,
binary=True,
alpha=args.alpha,
encodeLayer=[400, 400],
parser.add_argument('--save',
type=str,
default="",
metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--name',
type=str,
default="ltvae",
metavar='N',
help='number of epochs to train (default: 10)')
args = parser.parse_args()
timestr = time.strftime("%Y%m%d-%H%M%S")
init_logging("logs/" + timestr + "-" + args.name + ".log")
mnist_train = MNISTBinarized('../dataset/mnist', train=True, download=True)
mnist_test = MNISTBinarized('../dataset/mnist', train=False)
train_loader = torch.utils.data.DataLoader(mnist_train,
batch_size=args.batch_size,
shuffle=False,
num_workers=0)
test_loader = torch.utils.data.DataLoader(mnist_test,
batch_size=args.batch_size,
shuffle=False,
num_workers=0)
z_dim = 20
ltvae = LTVAE(input_dim=784,
z_dim=z_dim,
binary=True,