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.ReLU(),
)
self.code = nn.Sequential(
nn.Linear(
64 * (self.input_size // 2) * (self.input_size // 2), 32
), # bn and relu are excluded since code is used in pullaway_loss
)
self.fc = nn.Sequential(
nn.Linear(32,
64 * (self.input_size // 2) * (self.input_size // 2)),
nn.BatchNorm1d(64 * (self.input_size // 2) *
(self.input_size // 2)),
nn.ReLU(),
)
self.deconv = nn.Sequential(
nn.ConvTranspose2d(64, self.output_dim, 4, 2, 1),
# nn.Sigmoid(),
)
utilis.initialize_weights(self)
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.fc = nn.Sequential(
nn.Linear(500, 32),
nn.Linear(32, 500),
)
utilis.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, 2),
)
utilis.initialize_weights(self)
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.fc = nn.Sequential(
utils.spectral_norm(nn.Linear(2, 128)),
nn.ReLU(),
utils.spectral_norm(nn.Linear(128, 128)),
nn.ReLU(),
utils.spectral_norm(nn.Linear(128, self.output_dim)),
nn.Sigmoid(),
)
utilis.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, 128),
nn.Tanh(),
nn.Linear(128, 128),
nn.Tanh(),
nn.Linear(128, 2),
)
utilis.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.inputsize = input_size
d = 128
self.deconv = nn.Sequential(
nn.ConvTranspose2d(self.input_dim, d * 8, 4, 1, 0),
nn.BatchNorm2d(d * 8), nn.ReLU(),
nn.ConvTranspose2d(d * 8, d * 4, 4, 2, 1), nn.BatchNorm2d(d * 4),
nn.ReLU(), nn.ConvTranspose2d(d * 4, d * 2, 4, 2, 1),
nn.BatchNorm2d(d * 2), nn.ReLU(),
nn.ConvTranspose2d(d * 2, d, 4, 2, 1), nn.BatchNorm2d(d),
nn.ReLU(), nn.ConvTranspose2d(d, self.output_dim, 4, 2, 1),
nn.Tanh())
utilis.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())
utilis.initialize_weights(self)
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),
)
utilis.initialize_weights(self)
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
d = 128
self.conv = nn.Sequential(
nn.Conv2d(self.input_dim, d, 4, 2, padding=1), #1
nn.LeakyReLU(0.2),
nn.Conv2d(d, d * 2, 4, 2, 1), #2
nn.BatchNorm2d(d * 2),
nn.LeakyReLU(0.2),
nn.Conv2d(d * 2, d * 4, 4, 2, 1), #3
nn.BatchNorm2d(d * 4),
nn.LeakyReLU(0.2),
nn.Conv2d(d * 4, d * 8, 4, 2, 1), #4
nn.BatchNorm2d(d * 8),
nn.LeakyReLU(0.2),
nn.Conv2d(d * 8, 1, 4, 1, 0), #5
nn.Sigmoid())
utilis.initialize_weights(self)