def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
'''m = OrderedDict()
m['conv1'] = conv3x3(inplanes, planes, stride)
m['bn1'] = nn.BatchNorm2d(planes)
m['relu1'] = nn.ReLU(inplace=True)
m['conv2'] = conv3x3(planes, planes)
m['bn2'] = nn.BatchNorm2d(planes)
self.group1 = nn.Sequential(m)'''
'''self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)'''
self.conv1 = MaskedConv2d(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = MaskedConv2d(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
#self.relu = nn.Sequential(nn.ReLU(inplace=True))
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = MaskedConv2d(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.scale1 = ScaleLayer2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = MaskedConv2d(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.scale2 = ScaleLayer2d(planes)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet_AutoML, self).__init__()
self.conv1 = MaskedConv2d(3,
self.inplanes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(self.inplanes)
self.scale1 = ScaleLayer2d(self.inplanes)
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.avgpool = nn.AvgPool2d(kernel_size=7, stride=1, padding=0)
self.fc = MaskedLinear(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 conv3x3(in_planes, out_planes, stride=1):
# "3x3 convolution with padding"
#return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)
return MaskedConv2d(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
'''m = OrderedDict()
m['conv1'] = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
m['bn1'] = nn.BatchNorm2d(planes)
m['relu1'] = nn.ReLU(inplace=True)
m['conv2'] = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
m['bn2'] = nn.BatchNorm2d(planes)
m['relu2'] = nn.ReLU(inplace=True)
m['conv3'] = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
m['bn3'] = nn.BatchNorm2d(planes * 4)
self.group1 = nn.Sequential(m)'''
'''self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)'''
self.conv1 = MaskedConv2d(inplanes, 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,
planes * 4,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
#self.relu = nn.Sequential(nn.ReLU(inplace=True))
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = MaskedConv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.scale1 = ScaleLayer2d(planes)
self.conv2 = MaskedConv2d(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.scale2 = ScaleLayer2d(planes)
self.conv3 = MaskedConv2d(planes,
planes * Bottleneck.expansion,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(planes * Bottleneck.expansion)
self.scale3 = ScaleLayer2d(planes * Bottleneck.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
'''m = OrderedDict()
m['conv1'] = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
m['bn1'] = nn.BatchNorm2d(64)
m['relu1'] = nn.ReLU(inplace=True)
m['maxpool'] = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.group1= nn.Sequential(m)'''
#self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.conv1 = MaskedConv2d(3,
64,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
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.avgpool = nn.Sequential(nn.AvgPool2d(7))
self.avgpool = nn.AvgPool2d(kernel_size=7, stride=1, padding=0)
'''self.group2 = nn.Sequential(
OrderedDict([
('fc', nn.Linear(512 * block.expansion, num_classes))
])
)'''
#self.fc = nn.Linear(512 * block.expansion, num_classes)
self.fc = MaskedLinear(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 _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),
MaskedConv2d(self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False),
nn.BatchNorm2d(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)