def __init__(self):
super(Network, self).__init__()
self.convs = nn.Sequential(
nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(2),
NONLocalBlock2D(in_channels=32),
nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(2),
NONLocalBlock2D(in_channels=64),
nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(2),
)
self.fc = nn.Sequential(
nn.Linear(in_features=128*3*3, out_features=256),
nn.ReLU(),
nn.Dropout(0.5),
nn.Linear(in_features=256, out_features=10)
)
def __init__(self):
super(ResNet50Tiny, self).__init__()
self.layer0 = nn.Sequential(
nn.Conv2d(3,
32,
kernel_size=(3, 3),
stride=1,
padding=1,
bias=False), nn.BatchNorm2d(32), nn.ReLU(inplace=True))
self.inplanes = 32
self.layer1 = self._make_layer(32, 3, [2, 2])
self.layer2 = self._make_layer(64, 4, [2, 2])
self.layer3 = self._make_layer(128, 6, [2, 1])
self.layer4 = self._make_layer(256, 6, [2, 1])
self.non_local_4 = NONLocalBlock2D(256,
sub_sample=False,
bn_layer=True)
self.layer5 = self._make_layer(512, 3, [2, 1])
self.non_local_5 = NONLocalBlock2D(512,
sub_sample=False,
bn_layer=True)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight,
mode="fan_out",
nonlinearity="relu")
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)