def __init__(self, input_dim=1, output_dim=1, input_size=32):
super(Discriminator, self).__init__()
self.input_dim = input_dim
self.output_dim = output_dim
self.input_size = input_size
self.conv = nn.Sequential(
nn.Conv2d(self.input_dim, 64, 4, 2, 1),
nn.LeakyReLU(0.2),
nn.Conv2d(64, 128, 4, 2, 1),
nn.BatchNorm2d(128),
nn.LeakyReLU(0.2),
)
self.fc = nn.Sequential(
nn.Linear(128 * (self.input_size // 4) * (self.input_size // 4),
1024),
nn.BatchNorm1d(1024),
nn.LeakyReLU(0.2),
nn.Linear(1024, self.output_dim),
# nn.Sigmoid(),
)
utils.initialize_weights(self)
def __init__(self, input_dim=1, output_dim=1, input_size=32, cuda=False):
super(Discriminator, self).__init__()
self.input_dim = input_dim
self.output_dim = output_dim
self.input_size = input_size
config = Munch.fromDict(
dict(cuda=cuda,
model=dict(linear=dict(bjorck_beta=0.5,
bjorck_iter=12,
bjorck_order=1,
safe_scaling=True))))
self.conv = nn.Sequential(
# Conv.
BjorckConv2d(self.input_dim, 64, 4, 2, 1, config=config),
# Activ.
MaxMin(num_units=32, axis=1),
# Conv
BjorckConv2d(64, 128, 4, 2, 1, config=config),
# Activ.
MaxMin(num_units=64, axis=1))
self.fc = nn.Sequential(
# Linear.
BjorckLinear(128 * (self.input_size // 4) * (self.input_size // 4),
1024,
config=config),
# Activ.
MaxMin(num_units=512),
# Linear.
BjorckLinear(1024, self.output_dim, config=config),
# nn.Sigmoid(),
)
utils.initialize_weights(self)
def __init__(self, input_dim=100, output_dim=1, input_size=32):
super(Generator, self).__init__()
self.input_dim = input_dim
self.output_dim = output_dim
self.input_size = input_size
self.fc = nn.Sequential(
nn.Linear(self.input_dim, 1024),
nn.BatchNorm1d(1024),
nn.ReLU(),
nn.Linear(1024,
128 * (self.input_size // 4) * (self.input_size // 4)),
nn.BatchNorm1d(128 * (self.input_size // 4) *
(self.input_size // 4)),
nn.ReLU(),
)
self.deconv = nn.Sequential(
nn.ConvTranspose2d(128, 64, 4, 2, 1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.ConvTranspose2d(64, self.output_dim, 4, 2, 1),
nn.Tanh(),
)
utils.initialize_weights(self)