def __init__(self, in_channel, out_channel, kernel, stride, padding):
super(Up2d, self).__init__()
self.c1 = nn.ConvTranspose2d(in_channel,
out_channel,
kernel_size=kernel,
stride=stride,
padding=padding)
self.n1 = nn.InstanceNorm2d(out_channel)
self.c2 = nn.ConvTranspose2d(in_channel,
out_channel,
kernel_size=kernel,
stride=stride,
padding=padding)
self.n2 = nn.InstanceNorm2d(out_channel)
def downsample(self, in_channels, out_channels, kernel_size, stride, padding):
convLayer = nn.Sequential(
nn.Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
),
nn.InstanceNorm2d(num_features=out_channels, affine=True),
GLU(),
)
return convLayer
def __init__(self, in_channels, out_channels, kernel_size, stride, padding):
super(DownSampleGenerator, self).__init__()
self.convLayer = nn.Sequential(
nn.Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
),
nn.InstanceNorm2d(num_features=out_channels, affine=True),
)
self.convLayer_gates = nn.Sequential(
nn.Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
),
nn.InstanceNorm2d(num_features=out_channels, affine=True),
)
def upsample(self, in_channels, out_channels, kernel_size, stride, padding):
self.convLayer = nn.Sequential(
nn.Conv2d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
),
nn.PixelShuffle(upscale_factor=2),
nn.InstanceNorm2d(num_features=out_channels // 4, affine=True),
GLU(),
)
return self.convLayer
