def __init__(self,
in_channels,
middle_channels,
out_channels,
is_deconv=True):
super(CenterBlock, self).__init__()
self.in_channels = in_channels
self.is_deconv = is_deconv
if self.is_deconv: #Dense Block
self.conv1 = conv3x3_bn_relu(in_channels, middle_channels)
self.conv2 = conv3x3_bn_relu(in_channels + middle_channels,
middle_channels)
self.convUp = nn.Sequential(
nn.ConvTranspose2d(in_channels + 2 * middle_channels,
out_channels,
kernel_size=4,
stride=2,
padding=1), nn.ReLU(inplace=True))
else:
self.convUp = nn.Unsample(scale_factor=2,
mode='bilinear',
align_corners=True),
self.conv1 = conv3x3_bn_relu(in_channels, middle_channels),
self.conv2 = conv3x3_bn_relu(in_channels + middle_channels,
out_channels)
def __init__(self, isize, input_nc, output_nc, ngf, n_extra_layers=0):
super(CDCGAN_G_nobn, self).__init__()
assert isize % 16 == 0, "isize has to be a multiple of 16"
self.up = nn.Unsample(isize, mode='bilinear')
cngf, tisize = ngf//2, 4
while tisize != isize:
cngf = cngf * 2
tisize = tisize * 2
main = nn.Sequential()
main.add_module('initial.{0}-{1}.convt'.format(input_nc, cngf),
nn.ConvTranspose2d(input_nc, cngf, 4, 1, 0, bias=False))
main.add_module('initial.{0}.relu'.format(cngf),
nn.ReLU(True))
csize, cndf = 4, cngf
while csize < isize//2:
main.add_module('pyramid.{0}-{1}.convt'.format(cngf, cngf//2),
nn.ConvTranspose2d(cngf, cngf//2, 4, 2, 1, bias=False))
main.add_module('pyramid.{0}.relu'.format(cngf//2),
nn.ReLU(True))
cngf = cngf // 2
csize = csize * 2
# Extra layers
for t in range(n_extra_layers):
main.add_module('extra-layers-{0}.{1}.conv'.format(t, cngf),
nn.Conv2d(cngf, cngf, 3, 1, 1, bias=False))
main.add_module('extra-layers-{0}.{1}.relu'.format(t, cngf),
nn.ReLU(True))
main.add_module('final.{0}-{1}.convt'.format(cngf, output_nc),
nn.ConvTranspose2d(cngf, output_nc, 4, 2, 1, bias=False))
main.add_module('final.{0}.tanh'.format(output_nc),
nn.Tanh())
self.main = main
def __init__(self):
super(AlbedoGenerationNet, self).__init__()
self.unsample = nn.Unsample(scale_factor=2, mode='bilinear')
self.conv1 = get_conv(128, 128, kernel_size=1)
self.conv2 = get_conv(128, 64, kernel_size=3, padding=1)
self.conv3 = get_conv(64, 3, kernel_size=1)