def __init__(self, block, layers, num_classes):
self.inplanes = 128
super(ResNet, self).__init__()
self.conv1 = conv3x3(3, 64, stride=2)
self.bn1 = BatchNorm2d(64)
self.relu1 = nn.ReLU(inplace=False)
self.conv2 = conv3x3(64, 64)
self.bn2 = BatchNorm2d(64)
self.relu2 = nn.ReLU(inplace=False)
self.conv3 = conv3x3(64, 128)
self.bn3 = BatchNorm2d(128)
self.relu3 = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.relu = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1, ceil_mode=True) # change
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=1, dilation=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation=4, multi_grid=(1,1,1)) # we do not apply multi-grid method here
# extra added layers
self.head = nn.Sequential(
nn.Conv2d(2048, 512, kernel_size=3, stride=1, padding=1),
InPlaceABNSync(512),
NonLocal2d(inplanes=512, ratio=256, downsample=False),
nn.Dropout2d(0.05)
)
self.cls = nn.Conv2d(512, num_classes, kernel_size=1, stride=1, padding=0, bias=True)
self.dsn = nn.Sequential(
nn.Conv2d(1024, 512, kernel_size=3, stride=1, padding=1),
InPlaceABNSync(512),
nn.Dropout2d(0.05),
nn.Conv2d(512, num_classes, kernel_size=1, stride=1, padding=0, bias=True)
)
def __init__(self, block, layers, num_classes):
self.inplanes = 128
super(ResNet, self).__init__()
self.conv1 = conv3x3(3, 64, stride=2)
self.bn1 = BatchNorm2d(64)
self.relu1 = nn.ReLU(inplace=False)
self.conv2 = conv3x3(64, 64)
self.bn2 = BatchNorm2d(64)
self.relu2 = nn.ReLU(inplace=False)
self.conv3 = conv3x3(64, 128)
self.bn3 = BatchNorm2d(128)
self.relu3 = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.relu = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(kernel_size=3,
stride=2,
padding=1,
ceil_mode=True) # change
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=1,
dilation=2)
self.layer4 = self._make_layer(block,
512,
layers[3],
stride=1,
dilation=4,
multi_grid=(1, 1, 1))
# extra added layers
self.context = nn.Sequential(
nn.Conv2d(2048, 512, kernel_size=3, stride=1, padding=1),
InPlaceABNSync(512),
BaseOC_Module(in_channels=512,
out_channels=512,
key_channels=256,
value_channels=256,
dropout=0.05,
sizes=([1])))
self.cls = nn.Conv2d(512,
num_classes,
kernel_size=1,
stride=1,
padding=0,
bias=True)
self.dsn = nn.Sequential(
nn.Conv2d(1024, 512, kernel_size=3, stride=1, padding=1),
InPlaceABNSync(512), nn.Dropout2d(0.05),
nn.Conv2d(512,
num_classes,
kernel_size=1,
stride=1,
padding=0,
bias=True))
def __init__(self, block, layers, num_classes):
self.inplanes = 128
super(ResNet, self).__init__()
self.conv1 = conv3x3(3, 64, stride=2)
self.bn1 = BatchNorm2d(64)
self.relu1 = nn.ReLU(inplace=False)
self.conv2 = conv3x3(64, 64)
self.bn2 = BatchNorm2d(64)
self.relu2 = nn.ReLU(inplace=False)
self.conv3 = conv3x3(64, 128)
self.bn3 = BatchNorm2d(128)
self.relu3 = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.relu = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1, ceil_mode=True) # change
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=1, dilation=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation=4, multi_grid=(1,2,4))
self.head = nn.Sequential(ASPPModule(2048),
nn.Conv2d(512, num_classes, kernel_size=1)
)
self.dsn = nn.Sequential(
nn.Conv2d(1024, 512, kernel_size=3, padding=1, bias=False),
InPlaceABNSync(512),
nn.Dropout2d(0.1),
nn.Conv2d(512, num_classes, kernel_size=1)
)
def __init__(self,
in_channels,
key_channels,
value_channels,
out_channels=None,
scale=1):
super(_PyramidSelfAttentionBlock, self).__init__()
self.scale = scale
self.in_channels = in_channels
self.out_channels = out_channels
self.key_channels = key_channels
self.value_channels = value_channels
if out_channels == None:
self.out_channels = in_channels
self.f_key = nn.Sequential(
nn.Conv2d(in_channels=self.in_channels,
out_channels=self.key_channels,
kernel_size=1,
stride=1,
padding=0), InPlaceABNSync(self.key_channels))
self.f_query = self.f_key
self.f_value = nn.Conv2d(in_channels=self.in_channels,
out_channels=self.value_channels,
kernel_size=1,
stride=1,
padding=0)
self.W = nn.Conv2d(in_channels=self.value_channels,
out_channels=self.out_channels,
kernel_size=1,
stride=1,
padding=0)
nn.init.constant(self.W.weight, 0)
nn.init.constant(self.W.bias, 0)
def __init__(self, in_channels, out_channels, dropout, sizes=([1])):
super(Pyramid_OC_Module, self).__init__()
self.group = len(sizes)
self.stages = []
self.stages = nn.ModuleList([
self._make_stage(in_channels, out_channels, in_channels // 2,
in_channels, size) for size in sizes
])
self.conv_bn_dropout = nn.Sequential(
nn.Conv2d(2 * in_channels * self.group,
out_channels,
kernel_size=1,
padding=0), InPlaceABNSync(out_channels),
nn.Dropout2d(dropout))
self.up_dr = nn.Sequential(
nn.Conv2d(in_channels,
in_channels * self.group,
kernel_size=1,
padding=0), InPlaceABNSync(in_channels * self.group))
def __init__(self,
in_channels,
out_channels,
key_channels,
value_channels,
dropout,
sizes=([1])):
super(BaseOC_Module, self).__init__()
self.stages = []
self.stages = nn.ModuleList([
self._make_stage(in_channels, out_channels, key_channels,
value_channels, size) for size in sizes
])
self.conv_bn_dropout = nn.Sequential(
nn.Conv2d(2 * in_channels, out_channels, kernel_size=1, padding=0),
InPlaceABNSync(out_channels), nn.Dropout2d(dropout))
def __init__(self, features, out_features=512, dilations=(12, 24, 36)):
super(ASP_OC_Module, self).__init__()
self.context = nn.Sequential(
nn.Conv2d(features,
out_features,
kernel_size=3,
padding=1,
dilation=1,
bias=True), InPlaceABNSync(out_features),
BaseOC_Context_Module(in_channels=out_features,
out_channels=out_features,
key_channels=out_features // 2,
value_channels=out_features,
dropout=0,
sizes=([2])))
self.conv2 = nn.Sequential(
nn.Conv2d(features,
out_features,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_features))
self.conv3 = nn.Sequential(
nn.Conv2d(features,
out_features,
kernel_size=3,
padding=dilations[0],
dilation=dilations[0],
bias=False), InPlaceABNSync(out_features))
self.conv4 = nn.Sequential(
nn.Conv2d(features,
out_features,
kernel_size=3,
padding=dilations[1],
dilation=dilations[1],
bias=False), InPlaceABNSync(out_features))
self.conv5 = nn.Sequential(
nn.Conv2d(features,
out_features,
kernel_size=3,
padding=dilations[2],
dilation=dilations[2],
bias=False), InPlaceABNSync(out_features))
self.conv_bn_dropout = nn.Sequential(
nn.Conv2d(out_features * 5,
out_features,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_features),
nn.Dropout2d(0.1))
def __init__(self,
backbone='ResNet50',
pyramid_pooling='deeplabv3',
embedding=128,
batch_mode='sync'):
super(InterFrameNet, self).__init__()
if pyramid_pooling == 'deeplabv3':
self.features = ResNetDeepLabv3(backbone,
num_classes=embedding,
batch_mode=batch_mode)
elif pyramid_pooling == 'pspnet':
raise RuntimeError('Pooling module not implemented')
else:
raise RuntimeError('Unknown pyramid pooling module')
self.cls = nn.Sequential(
nn.Conv2d(2 * embedding,
embedding,
kernel_size=1,
stride=1,
padding=0), InPlaceABNSync(embedding),
nn.Dropout2d(0.10),
nn.Conv2d(embedding, 1, kernel_size=1, stride=1, padding=0))
def __init__(self, features, hidden_features=512, out_features=512, dilations=(12, 24, 36)):
super(ASPPModule, self).__init__()
self.conv1 = nn.Sequential(nn.Conv2d(features, hidden_features, kernel_size=1, bias=False),
InPlaceABNSync(hidden_features))
self.conv2 = nn.Sequential(nn.Conv2d(features, hidden_features, kernel_size=3, padding=dilations[0], dilation=dilations[0], bias=False),
InPlaceABNSync(hidden_features))
self.conv3 = nn.Sequential(nn.Conv2d(features, hidden_features, kernel_size=3, padding=dilations[1], dilation=dilations[1], bias=False),
InPlaceABNSync(hidden_features))
self.conv4 = nn.Sequential(nn.Conv2d(features, hidden_features, kernel_size=3, padding=dilations[2], dilation=dilations[2], bias=False),
InPlaceABNSync(hidden_features))
self.image_pooling = nn.Sequential(nn.AdaptiveAvgPool2d((1,1)),
nn.Conv2d(features, hidden_features, kernel_size=1, bias=False),
InPlaceABNSync(hidden_features))
self.conv_bn_dropout = nn.Sequential(
nn.Conv2d(hidden_features * 5, out_features, kernel_size=1, bias=False),
InPlaceABNSync(out_features),
nn.Dropout2d(0.1)
)
def __init__(self):
super(ASPP, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.conv_img = nn.Sequential(nn.Conv2d(4*512, 512, kernel_size=1, padding=0, dilation=1, bias=False),
InPlaceABNSync(512))
self.conv1 = nn.Sequential(nn.Conv2d(4*512, 512, kernel_size=1, padding=0, dilation=1, bias=False),
InPlaceABNSync(512))
self.conv2 = nn.Sequential(nn.Conv2d(4*512, 512, kernel_size=3, padding=12, dilation=12, bias=False),
InPlaceABNSync(512))
self.conv3 = nn.Sequential(nn.Conv2d(4*512, 512, kernel_size=3, padding=24, dilation=24, bias=False),
InPlaceABNSync(512))
self.conv4 = nn.Sequential(nn.Conv2d(4*512, 512, kernel_size=3, padding=36, dilation=36, bias=False),
InPlaceABNSync(512))
self.conv_bn_dropout = nn.Sequential(nn.Conv2d(5*512, 512, kernel_size=1, padding=0, dilation=1, bias=False),
InPlaceABNSync(512),
nn.Dropout2d(0.1))
