def __init__(self):
super(DecodeNet, self).__init__()
convList = []
convList.append(
baseNet.SampleNet(downSample=False,
in_channels=16,
out_channels=32))
convList.append(
baseNet.SampleNet(downSample=False,
in_channels=32,
out_channels=64))
convList.append(
baseNet.SampleNet(downSample=False,
in_channels=64,
out_channels=128))
convList.append(
baseNet.SampleNet(downSample=False,
in_channels=128,
out_channels=256))
convList.append(nn.ConvTranspose2d(256, 16, 1))
convList.append(nn.LeakyReLU())
convList.append(nn.ConvTranspose2d(16, 1, 1))
convList.append(nn.LeakyReLU())
self.convList = nn.Sequential(*convList)
def __init__(self):
super(DecodeNet, self).__init__()
self.tconv_channels_down = nn.ConvTranspose2d(256, 1, 1)
convList = []
convList.append(baseNet.SampleNet(downSample=False, in_channels=16, out_channels=32))
convList.append(baseNet.SampleNet(downSample=False, in_channels=32, out_channels=64))
convList.append(baseNet.SampleNet(downSample=False, in_channels=64, out_channels=256, kernel_size=4, stride=4))
self.convList = nn.Sequential(*convList)
def __init__(self):
super(EncodeNet, self).__init__()
self.conv_channels_up = nn.Conv2d(1, 256, 1)
convList = []
convList.append(baseNet.SampleNet(downSample=True, in_channels=256, out_channels=64, kernel_size=4, stride=4))
convList.append(baseNet.SampleNet(downSample=True, in_channels=64, out_channels=32))
convList.append(baseNet.SampleNet(downSample=True, in_channels=32, out_channels=16))
self.convList = nn.Sequential(*convList)
def __init__(self, channelsList):
super(EncodeNet, self).__init__()
self.conv_channels_up = nn.Conv2d(1, channelsList[0], 1)
convList = []
for i in range(channelsList.__len__() - 1):
convList.append(baseNet.SampleNet(downSample=True, in_channels=channelsList[i], out_channels=channelsList[i+1]))
print(channelsList[i], channelsList[i+1])
self.convList = nn.Sequential(*convList)
def __init__(self, dim_z, device):
super(Generator, self).__init__()
self.fc1 = nn.Linear(dim_z, 2048)
self.fc2 = nn.Linear(2048, 64 * 8 * 8)
self.tconv_channels_down = nn.ConvTranspose2d(256, 3, 1)
convList = []
convList.append(
baseNet.SampleNet(downSample=False,
in_channels=64,
out_channels=128,
device=device))
convList.append(
baseNet.SampleNet(downSample=False,
in_channels=128,
out_channels=256,
device=device))
self.convList = nn.Sequential(*convList)
def __init__(self, channelsList):
super(DecodeNet, self).__init__()
self.tconv_channels_down = nn.ConvTranspose2d(channelsList[-1], 1, 1)
convList = []
for i in range(channelsList.__len__() - 1):
convList.append(
baseNet.SampleNet(downSample=False, in_channels=channelsList[i], out_channels=channelsList[i + 1]))
print(channelsList[i], channelsList[i + 1])
self.convList = nn.Sequential(*convList)
def __init__(self, dim_z, device):
super(Encoder, self).__init__()
self.dim_z = dim_z
self.conv_channels_up = nn.Conv2d(3, 256, 1)
convList = []
convList.append(
baseNet.SampleNet(downSample=True,
in_channels=256,
out_channels=128,
device=device))
convList.append(
baseNet.SampleNet(downSample=True,
in_channels=128,
out_channels=64,
device=device))
self.convList = nn.Sequential(*convList)
self.fc1 = nn.Linear(64 * 8 * 8, 2048)
self.fc2 = nn.Linear(2048, dim_z * 2)
def __init__(self):
super(DecodeNet, self).__init__()
self.tconv_channels_down = nn.ConvTranspose2d(512, 16, 1, groups=16)
convList = []
for i in range(3):
convList.append(
baseNet.SampleNet(downSample=False,
in_channels=512,
out_channels=512,
groups=16))
self.convList = nn.Sequential(*convList)
def __init__(self):
super(EncodeNet, self).__init__()
self.conv_channels_up = nn.Conv2d(16, 512, 1, groups=16)
convList = []
for i in range(3):
convList.append(
baseNet.SampleNet(downSample=True,
in_channels=512,
out_channels=512,
groups=16))
self.convList = nn.Sequential(*convList)
def __init__(self):
super(EncodeNet, self).__init__()
convList = []
convList.append(nn.Conv2d(1, 64, 1))
convList.append(nn.LeakyReLU())
convList.append(
baseNet.ResNet(transpose=False,
channels=64,
kernel_size=3,
padding=1))
convList.append(
baseNet.SampleNet(downSample=True, in_channels=64, out_channels=1))
self.convList = nn.Sequential(*convList)
def __init__(self):
super(DecodeNet, self).__init__()
self.conv_up = baseNet.SampleNet(downSample=False,
in_channels=3,
out_channels=64)
convList = []
for i in range(4):
convList.append(
baseNet.ResNet(transpose=True,
channels=64,
kernel_size=3,
padding=1))
self.convList = nn.Sequential(*convList)
self.conv_channels_down = nn.ConvTranspose2d(64, 3, 1)
