def __init__(self,
nclass,
in_channels,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_ACFHead, self).__init__()
with self.name_scope():
self.aspp = ASPPModule(512,
in_channels,
norm_layer,
norm_kwargs,
rates=(12, 24, 36),
pool_branch=False)
self.coarse_head = FCNHead(nclass,
512,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.acf = _ACFModule(512,
512,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.head = FCNHead(nclass,
1024,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
backbone='mobilenet_v2_1_0',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=True,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(FCNMobileNet, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = FCNHead(nclass=nclass,
in_channels=self.stage_channels[3],
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
if self.aux:
self.aux_head = FCNHead(nclass=nclass,
in_channels=self.stage_channels[2],
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
decoder_capacity,
input_height,
input_width,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_LadderHead, self).__init__()
with self.name_scope():
self.conv_c4 = ConvBlock(decoder_capacity,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs,
activation='relu')
self.fusion_c3 = LateralFusion(decoder_capacity,
input_height // 16,
input_width // 16,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_c2 = LateralFusion(decoder_capacity,
input_height // 8,
input_width // 8,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_c1 = LateralFusion(decoder_capacity,
input_height // 4,
input_width // 4,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.seg_head = FCNHead(nclass, decoder_capacity, norm_layer,
norm_kwargs)
def __init__(self,
nclass,
backbone='densnet169',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(LadderDenseNet, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
decoder_capacity = 128
with self.name_scope():
self.head = _LadderHead(nclass,
decoder_capacity,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs,
input_height=self._up_kwargs['height'],
input_width=self._up_kwargs['width'])
if self.aux:
self.auxlayer = FCNHead(nclass,
in_channels=decoder_capacity,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
height=60,
width=60,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
use_sigmoid=True):
super(_AttentionHead, self).__init__()
self.sigmoid = use_sigmoid
self.up_kwargs = {'height': height, 'width': width}
with self.name_scope():
self.seg_head = FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.conv3x3 = ConvBlock(512,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs,
activation='relu')
if use_sigmoid:
self.conv1x1 = nn.Conv2D(1, 1, in_channels=512)
else:
self.conv1x1 = nn.Conv2D(2, 1, in_channels=512)
def __init__(self,
nclass,
input_height,
input_width,
capacity=256,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_NextHead, self).__init__()
with self.name_scope():
self.conv_c4 = ConvBlock(capacity,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_16x = LateralFusion(capacity,
input_height // 16,
input_width // 16,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_8x = LateralFusion(capacity,
input_height // 8,
input_width // 8,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.seg_head = FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
backbone='resnet50',
aux=False,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=True,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(UNet, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=False,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = _NextHead(nclass,
self._up_kwargs['height'],
self._up_kwargs['width'],
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
if self.aux:
self.auxlayer = FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
backbone='resnet50',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(PSPNet, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=True,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = _PyramidHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs,
height=self._up_kwargs['height'] // 8,
width=self._up_kwargs['width'] // 8)
if self.aux:
self.auxlayer = FCNHead(nclass=nclass,
in_channels=1024,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
in_channels,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_DeepLabHead, self).__init__()
with self.name_scope():
self.aspp = ASPPModule(256,
in_channels,
norm_layer,
norm_kwargs,
rates=(12, 24, 36))
self.conv_c1 = ConvModule2d(48,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.conv3x3 = ConvModule2d(256,
3,
1,
1,
in_channels=304,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.drop = nn.Dropout(0.5)
self.head = FCNHead(nclass, 256, norm_layer, norm_kwargs)
def __init__(self,
nclass,
backbone='resnet18',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(SwiftResNet, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=False,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = _SwiftNetHead(nclass,
self.base_channels[3],
norm_layer=norm_layer,
norm_kwargs=norm_kwargs,
input_height=self._up_kwargs['height'],
input_width=self._up_kwargs['width'])
if self.aux:
self.auxlayer = FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
backbone='resnet50',
aux=False,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=True,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(FaPN, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=False,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = _FaPNHead(nclass,
self.stage_channels,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
if self.aux:
self.aux_head = FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
backbone='resnet50',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(DenseASPP, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=True,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = _DenseASPPHead(nclass, 2048, norm_layer, norm_kwargs)
if self.aux:
self.auxlayer = FCNHead(nclass, 1024, norm_layer, norm_kwargs)
def __init__(self,
nclass,
in_channels,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
height=60,
width=60):
super(_DeepLabHead, self).__init__()
self.up_kwargs = {'height': height, 'width': width}
with self.name_scope():
self.aspp = ASPP(256,
in_channels,
norm_layer,
norm_kwargs,
height // 2,
width // 2,
atrous_rates=(12, 24, 36))
self.conv_c1 = ConvBlock(48,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.conv3x3 = ConvBlock(256,
3,
1,
1,
in_channels=304,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.drop = nn.Dropout(0.5)
self.head = FCNHead(nclass, 256, norm_layer, norm_kwargs)
def __init__(self, nclass, capacity=512, attention=False, drop=.5,
norm_layer=nn.BatchNorm, norm_kwargs=None, height=120, width=120):
super(_CAHead, self).__init__()
self.up_kwargs = {'height': height, 'width': width}
self.attention = attention
self.gamma = 1.0
height = height // 2
width = width // 2
with self.name_scope():
# Chained Context Aggregation Module
self.gp = GlobalFlow(capacity, 2048, height, width, norm_layer, norm_kwargs)
self.cp1 = _ContextFlow(capacity, stride=2, norm_layer=norm_layer,
norm_kwargs=norm_kwargs, height=height, width=width)
self.cp2 = _ContextFlow(capacity, stride=4, norm_layer=norm_layer,
norm_kwargs=norm_kwargs, height=height, width=width)
self.cp3 = _ContextFlow(capacity, stride=8, norm_layer=norm_layer,
norm_kwargs=norm_kwargs, height=height, width=width)
self.cp4 = _ContextFlow(capacity, stride=16, norm_layer=norm_layer,
norm_kwargs=norm_kwargs, height=height, width=width)
if self.attention:
self.selection = _FeatureSelection(256, in_channels=capacity, norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
else:
self.proj = ConvBlock(256, 3, 1, 1, in_channels=capacity, norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.drop = nn.Dropout(drop) if drop else None
# decoder
self.decoder = ConvBlock(48, 3, 1, 1, norm_layer=norm_layer, norm_kwargs=norm_kwargs)
self.conv3x3 = ConvBlock(256, 3, 1, 1, norm_layer=norm_layer, norm_kwargs=norm_kwargs)
# segmentation head
self.seg_head = FCNHead(nclass, norm_layer=norm_layer, norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
in_channels,
input_height,
input_width,
capacity=256,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_SwiftNetHead, self).__init__()
with self.name_scope():
self.ppool = PyramidPooling(in_channels, input_height // 32,
input_width // 32, norm_layer,
norm_kwargs)
self.conv_c4 = ConvBlock(capacity,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_c3 = LateralFusion(capacity,
input_height // 16,
input_width // 16,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_c2 = LateralFusion(capacity,
input_height // 8,
input_width // 8,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_c1 = LateralFusion(capacity,
input_height // 4,
input_width // 4,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.seg_head = FCNHead(nclass, capacity, norm_layer, norm_kwargs)
def __init__(self,
nclass,
backbone='xception65',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=True,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(DeepLabv3Plus, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=True,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = _DeepLabHead(nclass,
2048,
norm_layer,
norm_kwargs,
height=self._up_kwargs['height'] // 4,
width=self._up_kwargs['width'] // 4)
if self.aux:
self.auxlayer = FCNHead(nclass, 728, norm_layer, norm_kwargs)
def __init__(self,
nclass,
backbone='resnet50',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
dilate=True,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(DeepLabv3, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.output_stride = 8 if dilate else 32
with self.name_scope():
self.head = _DeepLabHead(nclass, self.stage_channels[3],
norm_layer, norm_kwargs)
if self.aux:
self.aux_head = FCNHead(nclass, self.stage_channels[2],
norm_layer, norm_kwargs)
def __init__(self,
nclass,
channels,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_DFPModule, self).__init__()
with self.name_scope():
self.blk_4 = ConvModule2d(channels,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.blk_3 = ConvModule2d(channels,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.blk_2 = ConvModule2d(channels,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.blk_1 = ConvModule2d(channels,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.head = FCNHead(nclass,
channels * 5,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
def __init__(self,
nclass,
input_height,
input_width,
capacity=128,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_SwiftNetHead, self).__init__()
with self.name_scope():
self.conv1x1 = ConvBlock(capacity,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_32x = _LateralFusion(capacity,
input_height // 32,
input_width // 32,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_16x = _LateralFusion(capacity,
input_height // 16,
input_width // 16,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_8x = _LateralFusion(capacity,
input_height // 8,
input_width // 8,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.final = _LateralFusion(capacity,
input_height // 4,
input_width // 4,
True,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.seg_head = FCNHead(nclass, capacity, norm_layer, norm_kwargs)
def __init__(self,
nclass,
backbone='resnet18',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(BiSeNet, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=False,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.head = _BiSeNetHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs,
height=self._up_kwargs['height'] // 8,
width=self._up_kwargs['width'] // 8)
if self.aux:
self.auxlayer = FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs,
drop_out=.0)
def __init__(self,
nclass,
in_channels,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_DenseASPPHead, self).__init__()
with self.name_scope():
self.dense_aspp = DenseASPPBlock(256, in_channels, norm_layer,
norm_kwargs)
self.head = FCNHead(nclass, 256, norm_layer, norm_kwargs)
def __init__(self, nclass, norm_layer=nn.BatchNorm, norm_kwargs=None):
super(_AttaNetHead, self).__init__()
with self.name_scope():
self.afm = _AttentionFusionModule(128, norm_layer, norm_kwargs)
self.conv3x3 = ConvModule2d(128,
3,
1,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.sam = _StripAttentionModule(128, norm_layer, norm_kwargs)
self.seg = FCNHead(nclass, 128, norm_layer, norm_kwargs)
def __init__(self,
nclass,
in_channels,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_DeepLabHead, self).__init__()
with self.name_scope():
self.aspp = ASPPModule(256,
in_channels,
norm_layer,
norm_kwargs,
rates=(6, 12, 18))
self.head = FCNHead(nclass, 256, norm_layer, norm_kwargs)
def __init__(self,
nclass,
backbone='xception39',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(BiSeNetX, self).__init__(nclass, aux, height, width, base_size,
crop_size)
assert backbone == 'xception39', 'support only xception39 as the backbone.'
pretrained = xception39(pretrained_base,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.conv = pretrained.conv1
self.max_pool = pretrained.maxpool
self.layer1 = pretrained.layer1
self.layer2 = pretrained.layer2
self.layer3 = pretrained.layer3
self.head = _BiSeNetHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
if self.aux:
self.aux_head = HybridConcurrentIsolate()
self.aux_head.add(
FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs),
FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs))
def __init__(self,
nclass,
backbone='resnet18',
aux=True,
height=None,
width=None,
base_size=520,
crop_size=480,
pretrained_base=False,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
**kwargs):
super(BiSeNetR, self).__init__(nclass,
aux,
backbone,
height,
width,
base_size,
crop_size,
pretrained_base,
dilate=False,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
with self.name_scope():
self.head = _BiSeNetHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
if self.aux:
self.aux_head = HybridConcurrentIsolate()
self.aux_head.add(
FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs),
FCNHead(nclass,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs))
def __init__(self,
nclass,
in_channels,
capacity=256,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_SwiftNetHead, self).__init__()
with self.name_scope():
self.ppool = PPModule(in_channels, norm_layer, norm_kwargs)
self.conv_c4 = ConvModule2d(capacity,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_c3 = LateralFusion(capacity, norm_layer, norm_kwargs)
self.fusion_c2 = LateralFusion(capacity, norm_layer, norm_kwargs)
self.fusion_c1 = LateralFusion(capacity, norm_layer, norm_kwargs)
self.seg_head = FCNHead(nclass, capacity, norm_layer, norm_kwargs)
def __init__(self,
nclass,
in_channels,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
height=60,
width=60):
super(_DeepLabHead, self).__init__()
with self.name_scope():
self.aspp = ASPP(256,
in_channels,
norm_layer,
norm_kwargs,
height,
width,
atrous_rates=(12, 24, 36))
self.head = FCNHead(nclass, 256, norm_layer, norm_kwargs)
def __init__(self,
nclass,
height,
width,
norm_layer=nn.BatchNorm,
norm_kwargs=None,
activation='relu'):
super(_PyramidHead, self).__init__()
with self.name_scope():
self.pool = PyramidPooling(2048,
height,
width,
norm_layer,
norm_kwargs,
activation,
reduction=4)
self.seg_head = FCNHead(nclass, 4096, norm_layer, norm_kwargs)
def __init__(self,
nclass,
capacity=128,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_SwiftNetHead, self).__init__()
with self.name_scope():
self.conv1x1 = ConvModule2d(capacity,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_32x = _LateralFusion(capacity, norm_layer, norm_kwargs)
self.fusion_16x = _LateralFusion(capacity, norm_layer, norm_kwargs)
self.fusion_8x = _LateralFusion(capacity, norm_layer, norm_kwargs)
self.final = _LateralFusion(capacity,
norm_layer,
norm_kwargs,
is_final=True)
self.seg_head = FCNHead(nclass, capacity, norm_layer, norm_kwargs)
def __init__(self,
nclass,
decoder_capacity,
norm_layer=nn.BatchNorm,
norm_kwargs=None):
super(_LadderHead, self).__init__()
with self.name_scope():
self.conv_c4 = ConvModule2d(decoder_capacity,
1,
norm_layer=norm_layer,
norm_kwargs=norm_kwargs)
self.fusion_c3 = LateralFusion(decoder_capacity, norm_layer,
norm_kwargs)
self.fusion_c2 = LateralFusion(decoder_capacity, norm_layer,
norm_kwargs)
self.fusion_c1 = LateralFusion(decoder_capacity, norm_layer,
norm_kwargs)
self.seg_head = FCNHead(nclass, decoder_capacity, norm_layer,
norm_kwargs)