def __init__(self):
super(DecodeNet, self).__init__()
self.conv_channels_up = nn.Conv2d(16, 256, 1)
self.conv_channels_down = nn.Conv2d(256, 1, 1)
self.convList0 = baseNet.ResNet(transpose=False,
channels=256,
kernel_size=3,
padding=1)
self.convList1 = baseNet.ResNet(transpose=False,
channels=256,
kernel_size=3,
padding=1)
def __init__(self, channels):
super(EncodeNet, self).__init__()
self.conv_channels_up = nn.Conv2d(1, channels, 1)
convList = []
for i in range(4):
convList.append(pixelShuffleFunction.PixelUnshuffle(2))
if(i>=2):
convList.append(nn.Conv2d(channels * 4, channels, 1))
elif(i==0):
convList.append(nn.Conv2d(channels * 4, channels, 5, padding=2))
elif(i==1):
convList.append(nn.Conv2d(channels * 4, channels, 3, padding=1))
'''
i kernel padding
0 5 2
1 3 1
2 1 0
3 1 0
'''
convList.append(nn.LeakyReLU(inplace=True))
convList.append(nn.BatchNorm2d(channels))
convList.append(baseNet.ResNet(transpose=False, channels=channels, kernel_size=3, padding=1))
convList.append(nn.Conv2d(channels, 16, 1))
convList.append(nn.LeakyReLU(inplace=True))
self.convList = nn.Sequential(*convList)
def __init__(self):
super(RecNet, self).__init__()
self.conv_channels_up = nn.Conv2d(3, 64, 1)
convList = []
for i in range(32):
convList.append(baseNet.ResNet(transpose=False, channels=64, kernel_size=3, padding=1))
self.convList = nn.Sequential(*convList)
self.conv_channels_down = nn.Conv2d(64, 3, 1)
def __init__(self, channels, depth):
super(blockPredictNet, self).__init__()
self.conv_channels_up = nn.Conv2d(3, channels, 1)
convList = []
for i in range(depth):
convList.append(
baseNet.ResNet(transpose=False,
channels=channels,
kernel_size=3,
padding=1))
self.conv_channels_down = nn.Conv2d(channels, 1, 1)
self.convList = nn.Sequential(*convList)
def __init__(self, channels):
super(DecodeNet, self).__init__()
self.conv_channels_down = nn.Conv2d(channels, 1, 1)
convList = []
convList.append(nn.Conv2d(16, channels, 1))
convList.append(nn.LeakyReLU(inplace=True))
for i in range(4):
convList.append(baseNet.ResNet(transpose=False, channels=channels, kernel_size=3, padding=1))
convList.append(nn.BatchNorm2d(channels))
convList.append(nn.Conv2d(channels, channels*4, 1))
convList.append(nn.LeakyReLU(inplace=True))
convList.append(nn.PixelShuffle(2))
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)
def __init__(self, channels):
super(EncodeNet, self).__init__()
self.conv_channels_up = nn.Conv2d(1, channels, 1)
convList = []
for i in range(4):
convList.append(pixelShuffleFunction.PixelUnshuffle(2))
convList.append(nn.Conv2d(channels * 4, channels, 1))
convList.append(nn.LeakyReLU())
convList.append(
baseNet.ResNet(transpose=False,
channels=channels,
kernel_size=3,
padding=1))
convList.append(nn.Conv2d(channels, 16, 1))
convList.append(nn.LeakyReLU())
self.convList = nn.Sequential(*convList)