def __init__(self, dimension, deconv = UpsampleDeConv, activation = nn.LeakyReLU(), drop_out : float = 0.5):
super(AdelaideResidualGenerator, self).__init__(dimension, deconv, activation, drop_out)
self.enc1 = ResidualBlock(dimension, 64, stride = 2,activation=activation)
self.enc2 = ResidualBlock(64, 128, stride = 2,activation=activation)
self.enc3 = ResidualBlock(128, 256, stride = 2,activation=activation)
self.enc4 = ResidualBlock(256, 512, stride = 2,activation=activation)
self.enc5 = ResidualBlock(512, 512, stride = 2,activation=activation)
def __init__(self,dimension, deconv = UpsampleDeConv, activation = nn.LeakyReLU(), drop_out : float = 0.5):
super(AdelaideFastGenerator, self).__init__(dimension, deconv, activation, drop_out)
self.enc1 = ResidualBlock(dimension, 16, stride = 2, activation=activation)
self.enc2 = ResidualBlock(16, 32, stride = 2, activation=activation)
self.enc3 = ResidualBlock(32, 64, stride = 2, activation=activation)
self.enc4 = ResidualBlock(64, 128, stride = 2, activation=activation)
self.enc5 = ResidualBlock(128, 256, stride = 2, activation=activation)
self.dec1 = SimpleDecoder(256, 128, deconv=deconv)
self.dec2 = SimpleDecoder(128, 64, deconv=deconv)
self.dec3 = SimpleDecoder(64, 32, deconv=deconv)
self.dec4 = SimpleDecoder(32, 16, deconv=deconv)
self.dec5 = SimpleDecoder(16, dimension, deconv=deconv)
def __init__(self,
dimension,
deconv=UpsampleDeConv,
activation=nn.LeakyReLU(),
drop_out: float = 0.5):
super(StanfordFastGenerator, self).__init__()
self.DEPTH_SIZE = int(3)
self.conv1 = BaseBlock(dimension,
LATENT_SPACE_8,
9,
1,
activation=activation,
drop_out=drop_out)
self.conv2 = BaseBlock(LATENT_SPACE_8,
LATENT_SPACE_4,
3,
2,
activation=activation,
drop_out=drop_out)
self.conv3 = BaseBlock(LATENT_SPACE_4,
LATENT_SPACE_2,
3,
2,
activation=activation,
drop_out=drop_out)
self.residual_blocks = nn.Sequential()
for i in range(0, self.DEPTH_SIZE):
self.residual_blocks.add_module(
str(i),
ResidualBlock(LATENT_SPACE_2,
LATENT_SPACE_2,
stride=1,
activation=activation))
self.deconv1 = deconv(LATENT_SPACE_2, LATENT_SPACE_4)
self.norm1 = torch.nn.BatchNorm2d(LATENT_SPACE_4, affine=True)
self.deconv2 = deconv(LATENT_SPACE_4, LATENT_SPACE_8)
self.norm2 = torch.nn.BatchNorm2d(LATENT_SPACE_8, affine=True)
self.refinement = nn.Sequential(
ConvLayer(LATENT_SPACE_8, LATENT_SPACE_8, kernel_size=3, stride=1),
torch.nn.BatchNorm2d(LATENT_SPACE_8, affine=True),
activation,
ConvLayer(LATENT_SPACE_8, LATENT_SPACE_8, kernel_size=3, stride=1),
torch.nn.BatchNorm2d(LATENT_SPACE_8, affine=True),
activation,
)
self.final = ConvLayer(LATENT_SPACE_8,
dimension,
kernel_size=9,
stride=1)
self.activation = activation
def __init__(self, dimension, deconv = UpsampleDeConv, activation = nn.LeakyReLU(), drop_out : float = 0.5):
super(MovaviResidualGenerator, self).__init__(dimension, deconv, activation, drop_out)
self.enc1 = ResidualBlock(dimension, 16, activation = activation, stride=2)
self.enc2 = ResidualBlock(16, 32, activation = activation, stride=2, drop_out=drop_out)
self.enc3 = ResidualBlock(32, 64, activation = activation, stride=2, drop_out=drop_out)
self.enc4 = ResidualBlock(64, 128, activation = activation, stride=2, drop_out=drop_out)
self.enc5 = ResidualBlock(128, 128, activation = activation, stride=2, drop_out=drop_out)
self.center = ResidualBlock(128, 128, activation = activation, stride=1, drop_out=drop_out)
def __init__(self,
dimension,
deconv=UpsampleDeConv,
activation=nn.LeakyReLU(),
drop_out: float = 0.5):
super(BerkeleyResidualGenerator,
self).__init__(dimension, deconv, activation, drop_out)
self.layer1 = ResidualBlock(dimension,
64,
stride=2,
activation=activation)
self.layer2 = ResidualBlock(64, 128, stride=2, activation=activation)
self.layer3 = ResidualBlock(128, 256, stride=2, activation=activation)
self.layer4 = ResidualBlock(256, 512, stride=2, activation=activation)
self.layer5 = ResidualBlock(512, 512, stride=2, activation=activation)
self.layer6 = ResidualBlock(512, 512, stride=2, activation=activation)
def __init__(self,
dimension,
deconv=UpsampleDeConv,
activation=nn.LeakyReLU(),
drop_out: float = 0.5):
super(StanfordSupremeGenerator, self).__init__()
self.DEPTH_SIZE = int(9)
self.conv1 = BaseBlock(dimension,
64,
9,
1,
activation=activation,
drop_out=drop_out)
self.conv2 = BaseBlock(64,
128,
3,
2,
activation=activation,
drop_out=drop_out)
self.conv3 = BaseBlock(128,
256,
3,
2,
activation=activation,
drop_out=drop_out)
self.residual_blocks = nn.Sequential()
for i in range(0, self.DEPTH_SIZE):
self.residual_blocks.add_module(
str(i), ResidualBlock(256,
256,
stride=1,
activation=activation))
self.deconv1 = deconv(512, 128)
self.norm1 = torch.nn.BatchNorm2d(128, affine=True)
self.deconv2 = deconv(256, 64)
self.norm2 = torch.nn.BatchNorm2d(64, affine=True)
self.final = ConvLayer(64, dimension, kernel_size=9, stride=1)
self.activation = activation
def __init__(self, dimension, deconv = UpsampleDeConv, activation = nn.LeakyReLU(), drop_out : float = 0.5):
super(MovaviStrongGenerator, self).__init__(dimension, deconv, activation, drop_out)
self.enc1 = ResidualBlock(dimension, 32, activation=activation, stride=2, drop_out=drop_out)
self.enc2 = ResidualBlock(32, 64, activation=activation, stride=2, drop_out=drop_out)
self.enc3 = ResidualBlock(64, 128, activation=activation, stride=2, drop_out=drop_out)
self.enc4 = ResidualBlock(128, 256, activation=activation, stride=2, drop_out=drop_out)
self.enc5 = ResidualBlock(256, 256, activation=activation, stride=2, drop_out=drop_out)
self.center = ResidualBlock(256, 256, activation=activation, stride=1, drop_out=drop_out)
self.dec6 = nn.Sequential(BaseBlock(512, 256, 3, 1, activation=activation, drop_out=drop_out),
BaseBlock(256, 256, 3, 1, activation=activation, drop_out=drop_out), deconv(256, 128))
self.dec7 = nn.Sequential(BaseBlock(384, 128, 3, 1, activation=activation, drop_out=drop_out),
BaseBlock(128, 128, 3, 1, activation=activation, drop_out=drop_out), deconv(128, 64))
self.dec8 = nn.Sequential(BaseBlock(192, 64, 3, 1, activation=activation, drop_out=drop_out),
BaseBlock(64, 64, 3, 1, activation=activation, drop_out=drop_out), deconv(64, 32))
self.dec9 = nn.Sequential(BaseBlock(96, 32, 3, 1, activation=activation, drop_out=drop_out),
BaseBlock(32, 32, 3, 1, activation=activation, drop_out=drop_out), deconv(32, 32))
self.dec10 = deconv(32, 32)
self.final = ConvLayer(32, dimension, 3, 1)
def __init__(self,
dimension,
deconv=UpsampleDeConv,
activation=nn.LeakyReLU(),
drop_out: float = 0.5):
super(BerkeleyFastGenerator, self).__init__(dimension, deconv,
activation, drop_out)
self.layer1 = ResidualBlock(dimension,
16,
stride=2,
activation=activation)
self.layer2 = ResidualBlock(16, 32, stride=2, activation=activation)
self.layer3 = ResidualBlock(32, 64, stride=2, activation=activation)
self.layer4 = ResidualBlock(64, 128, stride=2, activation=activation)
self.layer5 = ResidualBlock(128, 256, stride=2, activation=activation)
self.layer6 = ResidualBlock(256, 512, stride=2, activation=activation)
self.layer7 = SimpleDecoder(512 * 1, 256, deconv=deconv)
self.layer8 = SimpleDecoder(256 * 2, 128, deconv=deconv)
self.layer9 = SimpleDecoder(128 * 2, 64, deconv=deconv)
self.layer10 = SimpleDecoder(64 * 2, 32, deconv=deconv)
self.layer11 = SimpleDecoder(32 * 2, 16, deconv=deconv)
self.layer12 = SimpleDecoder(16, dimension, deconv=deconv)