def __init__(self, args, in_channels, out_channels, stride=1):
super(ResBlockDiscriminator, self).__init__()
#self.conv1 = nn.Conv2d(in_channels, out_channels, 3, 1, padding=1)
self.conv1 = my.NormConv(in_channels,
out_channels,
3,
1,
padding=1,
adjustScale=False,
NScale=1,
T=args.T)
#self.conv2 = nn.Conv2d(out_channels, out_channels, 3, 1, padding=1)
self.conv2 = my.NormConv(out_channels,
out_channels,
3,
1,
padding=1,
adjustScale=False,
NScale=1,
T=args.T)
nn.init.xavier_uniform_(self.conv1.weight.data, 1.)
nn.init.xavier_uniform_(self.conv2.weight.data, 1.)
if stride == 1:
self.model = nn.Sequential(
nn.ReLU(),
# SpectralNorm(self.conv1),
self.conv1,
nn.ReLU(),
# SpectralNorm(self.conv2)
self.conv2)
else:
self.model = nn.Sequential(
nn.ReLU(),
# SpectralNorm(self.conv1),
self.conv1,
nn.ReLU(),
#SpectralNorm(self.conv2),
self.conv2,
nn.AvgPool2d(2, stride=stride, padding=0))
self.bypass = nn.Sequential()
if stride != 1:
#self.bypass_conv = nn.Conv2d(in_channels,out_channels, 1, 1, padding=0)
self.bypass_conv = my.NormConv(in_channels,
out_channels,
1,
1,
padding=0,
adjustScale=False,
NScale=1,
T=args.T)
nn.init.xavier_uniform_(self.bypass_conv.weight.data, np.sqrt(2))
self.bypass = nn.Sequential(
# SpectralNorm(self.bypass_conv),
self.bypass_conv,
nn.AvgPool2d(2, stride=stride, padding=0))
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
#self.conv1 = conv3x3(inplanes, planes, stride)
self.conv1 = my.NormConv(inplanes, planes, 3, stride, padding=1, bias=False)
#self.bn1 = nn.BatchNorm2d(planes)
self.bn1 = my.Norm(planes)
self.relu = nn.ReLU(inplace=True)
#self.conv2 = conv3x3(planes, planes)
#self.conv2 = Conv2d_ONI(planes, planes, 3, stride=1, padding=1, bias=False, T=7)
self.conv2 = my.NormConv(planes, planes, 3, stride=1, padding=1, bias=False)
#self.bn2 = nn.BatchNorm2d(planes)
self.bn2 = my.Norm(planes)
self.downsample = downsample
self.stride = stride
def __init__(self, block, layers, num_classes=1000, **kwargs):
self.inplanes = 64
super(ResNet_var_ONI, self).__init__()
#self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.conv1 = my.NormConv(3,
64,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.bn1 = nn.BatchNorm2d(512 * block.expansion)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def __init__(self, args, in_channels, out_channels, stride=1):
super(FirstResBlockDiscriminator, self).__init__()
#self.conv1 = nn.Conv2d(in_channels, out_channels, 3, 1, padding=1)
self.conv1 = my.NormConv(in_channels,
out_channels,
3,
1,
padding=1,
adjustScale=False,
NScale=1,
T=args.T)
#self.conv2 = nn.Conv2d(out_channels, out_channels, 3, 1, padding=1)
self.conv2 = my.NormConv(out_channels,
out_channels,
3,
1,
padding=1,
adjustScale=False,
NScale=1,
T=args.T)
#self.bypass_conv = nn.Conv2d(in_channels, out_channels, 1, 1, padding=0)
self.bypass_conv = my.NormConv(in_channels,
out_channels,
1,
1,
padding=0,
adjustScale=False,
NScale=1,
T=args.T)
nn.init.xavier_uniform_(self.conv1.weight.data, 1.)
nn.init.xavier_uniform_(self.conv2.weight.data, 1.)
nn.init.xavier_uniform_(self.bypass_conv.weight.data, np.sqrt(2))
# we don't want to apply ReLU activation to raw image before convolution transformation.
self.model = nn.Sequential(
# SpectralNorm(self.conv1),
self.conv1,
nn.ReLU(),
# SpectralNorm(self.conv2),
self.conv2,
nn.AvgPool2d(2))
self.bypass = nn.Sequential(
nn.AvgPool2d(2),
# SpectralNorm(self.bypass_conv),
self.bypass_conv,
)
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck_var_ONI, self).__init__()
self.bn1 = nn.BatchNorm2d(inplanes)
#self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.conv1 = my.NormConv(inplanes, planes, kernel_size=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
#self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.conv2 = my.NormConv(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn3 = nn.BatchNorm2d(planes)
#self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.conv3 = my.NormConv(planes, planes * 4, kernel_size=1, bias=False)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def make_layers(cfg, batch_norm=False):
layers = []
in_channels = 3
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = my.NormConv(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
#nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False),
my.NormConv(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False, ONIRow_Fix=True),
#nn.BatchNorm2d(planes * block.expansion), )
my.Norm(planes * block.expansion), )
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def __init__(self,args):
super(Discriminator, self).__init__()
#self.conv1 = SpectralNorm(nn.Conv2d(channels, 64, 3, stride=1, padding=(1,1)))
self.conv1 = my.NormConv(channels, 64, 3, stride=1, padding=(1,1), bias=True, adjustScale=False, NScale=args.NScale, T=args.T)
#self.conv2 = SpectralNorm(nn.Conv2d(64, 64, 4, stride=2, padding=(1,1)))
self.conv2 = my.NormConv(64, 64, 4, stride=2, padding=(1,1), bias=True, adjustScale=False, NScale=args.NScale, T=args.T)
#self.conv3 = SpectralNorm(nn.Conv2d(64, 128, 3, stride=1, padding=(1,1)))
self.conv3 = my.NormConv(64, 128, 3, stride=1, padding=(1,1), bias=True, adjustScale=False, NScale=args.NScale, T=args.T)
#self.conv4 = SpectralNorm(nn.Conv2d(128, 128, 4, stride=2, padding=(1,1)))
self.conv4 = my.NormConv(128, 128, 4, stride=2, padding=(1,1), bias=True, adjustScale=False, NScale=args.NScale, T=args.T)
#self.conv5 = SpectralNorm(nn.Conv2d(128, 256, 3, stride=1, padding=(1,1)))
self.conv5 = my.NormConv(128, 256, 3, stride=1, padding=(1,1), bias=True, adjustScale=False, NScale=args.NScale, T=args.T)
#self.conv6 = SpectralNorm(nn.Conv2d(256, 256, 4, stride=2, padding=(1,1)))
self.conv6 = my.NormConv(256, 256, 4, stride=2, padding=(1,1), bias=True, adjustScale=False, NScale=args.NScale, T=args.T)
#self.conv7 = SpectralNorm(nn.Conv2d(256, 512, 3, stride=1, padding=(1,1)))
self.conv7 = my.NormConv(256, 512, 3, stride=1, padding=(1,1), bias=True, adjustScale=False, NScale=args.NScale, T=args.T)
self.fc = SpectralNorm(nn.Linear(w_g * w_g * 512, 1))