def __init__(self, init_scheme=nn.init.xavier_normal_):
super(MaskedLeNet, self).__init__(init_scheme=init_scheme)
self.conv1 = MaskedConv2d(3, 6, kernel_size=5)
self.conv2 = MaskedConv2d(6, 16, kernel_size=5)
self.fc1 = MaskedLinear(16 * 5 * 5, 120)
self.fc2 = MaskedLinear(120, 84)
self.fc3 = MaskedLinear(84, 10)
def __init__(self, in_planes, planes, dropout_rate, stride=1):
super(wide_basic, self).__init__()
self.bn1 = nn.BatchNorm2d(in_planes)
self.conv1 = MaskedConv2d(in_planes,
planes,
kernel_size=3,
padding=1,
bias=True)
self.dropout = nn.Dropout(p=dropout_rate)
self.bn2 = nn.BatchNorm2d(planes)
self.conv2 = MaskedConv2d(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=True)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes,
planes,
kernel_size=1,
stride=stride,
bias=True), )
def _make_layers(self, cfg, use_bn):
layers = []
in_channels = 3
for i, x in enumerate(cfg):
if x == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
if i == 0:
layers += [
MaskedConv2d(in_channels,
x,
kernel_size=3,
padding=1,
stride=2)
]
else:
layers += [
MaskedConv2d(in_channels, x, kernel_size=3, padding=1)
]
if use_bn:
layers += [nn.BatchNorm2d(x)]
layers += [nn.ReLU(inplace=True)]
in_channels = x
layers += [nn.AvgPool2d(kernel_size=1, stride=1)]
return nn.Sequential(*layers)
def __init__(self, in_planes, planes, stride=1):
super(Bottleneck, self).__init__()
self.conv1 = MaskedConv2d(in_planes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = MaskedConv2d(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = MaskedConv2d(planes,
self.expansion * planes,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion * planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes,
self.expansion * planes,
kernel_size=1,
stride=stride,
bias=False), nn.BatchNorm2d(self.expansion * planes))
def conv3x3(in_planes, out_planes, stride=1):
return MaskedConv2d(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=True)
def __init__(self, block, num_blocks, num_classes=200):
super(MaskedResNet_64, self).__init__()
self.in_planes = 64
self.conv1 = MaskedConv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.linear = MaskedLinear(512*block.expansion, num_classes)