def __init__(self, block, layers, num_classes=1000, using_moving_average=True, using_bn=True):
self.inplanes = 64
self.using_moving_average=using_moving_average
self.using_bn = using_bn
super(ResNetV2SN, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.sn1 = SwitchNorm2d(64, using_moving_average=self.using_moving_average, using_bn=self.using_bn)
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.sn_out = SwitchNorm2d(512 * block.expansion, using_moving_average=self.using_moving_average, using_bn=self.using_bn)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.drouput = nn.Dropout(p=0.5)
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, SwitchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def __init__(self, inplanes, planes, stride=1, downsample=None, using_moving_average=True, using_bn=True, last_gamma=True):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.sn1 = SwitchNorm2d(planes, using_moving_average=using_moving_average, using_bn=using_bn)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.sn2 = SwitchNorm2d(planes, using_moving_average=using_moving_average, using_bn=using_bn, last_gamma=last_gamma)
self.downsample = downsample
self.stride = stride
def __init__(self, inplanes, planes, stride=1, downsample=None, using_moving_average=True, using_bn=True, last_gamma=True):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.sn1 = SwitchNorm2d(planes, using_moving_average=using_moving_average, using_bn=using_bn)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
padding=1, bias=False)
self.sn2 = SwitchNorm2d(planes, using_moving_average=using_moving_average, using_bn=using_bn)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.sn3 = SwitchNorm2d(planes * 4, using_moving_average=using_moving_average, using_bn=using_bn, last_gamma=last_gamma)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
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),
SwitchNorm2d(planes * block.expansion, using_moving_average=self.using_moving_average,
using_bn=self.using_bn),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, using_moving_average=self.using_moving_average,
using_bn=self.using_bn, last_gamma=self.last_gamma))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, using_moving_average=self.using_moving_average,
using_bn=self.using_bn, last_gamma=self.last_gamma))
return nn.Sequential(*layers)
def NormFunc(*args, **kwargs):
return SwitchNorm2d(*args, **kwargs, eps=2e-5, momentum=0.9)