def __init__(self, in_dim, out_dim, scale):
super(sa_MagicModule, self).__init__()
self.atte_branch = nn.Sequential(nn.Conv2d(in_dim, out_dim, kernel_size=3, padding=1, dilation=1, bias=False),
InPlaceABNSync(out_dim),
SelfAttentionModule(in_dim=out_dim, out_dim=out_dim, key_dim=out_dim // 2,
value_dim=out_dim, scale=scale))
# TODO: change SE Module to Channel Attention Module
self.dilation_x = nn.Sequential(nn.Conv2d(in_dim, out_dim, kernel_size=1, padding=0, dilation=1, bias=False),
InPlaceABNSync(out_dim), SEModule(out_dim, reduction=16))
# self.dilation_x = nn.Sequential(nn.Conv2d(in_dim, out_dim, kernel_size=1, padding=0, dilation=1, bias=False),
# InPlaceABNSync(out_dim), ChannelAttentionModule(out_dim))
self.dilation_0 = nn.Sequential(ContextContrastedModule(in_dim, out_dim, rate=6),
SEModule(out_dim, reduction=16))
self.dilation_1 = nn.Sequential(ContextContrastedModule(in_dim, out_dim, rate=12),
SEModule(out_dim, reduction=16))
self.dilation_2 = nn.Sequential(ContextContrastedModule(in_dim, out_dim, rate=18),
SEModule(out_dim, reduction=16))
self.dilation_3 = nn.Sequential(ContextContrastedModule(in_dim, out_dim, rate=24),
SEModule(out_dim, reduction=16))
self.head_conv = nn.Sequential(nn.Conv2d(out_dim * 6, out_dim, kernel_size=1, padding=0, bias=False),
InPlaceABNSync(out_dim)
)
self.refine = nn.Sequential(nn.Conv2d(out_dim, out_dim, kernel_size=3, stride=1, padding=1, bias=False),
InPlaceABNSync(out_dim))
self.project = nn.Conv2d(6 * out_dim, 6, kernel_size=1, padding=0, bias=True)
def __init__(self, in_dim, out_dim, scale):
super(SEOCModule, self).__init__()
self.atte_branch = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=3,
padding=1,
dilation=1,
bias=True), InPlaceABNSync(out_dim),
SelfAttentionModule(in_dim=out_dim,
out_dim=out_dim,
key_dim=out_dim // 2,
value_dim=out_dim,
scale=scale))
self.dilation_0 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_1 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=3,
padding=12,
dilation=12,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_2 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=3,
padding=24,
dilation=24,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_3 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=3,
padding=36,
dilation=36,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.head_conv = nn.Sequential(
nn.Conv2d(out_dim * 5,
out_dim,
kernel_size=1,
stride=1,
padding=0,
bias=False), InPlaceABNSync(out_dim))
def __init__(self, fbody_cls):
super(AlphaFBDecoder, self).__init__()
self.conv1 = nn.Sequential(nn.Conv2d(512, 256, kernel_size=3, padding=1, stride=1, bias=False),
BatchNorm2d(256), nn.ReLU(inplace=False),
nn.Conv2d(256, 256, kernel_size=1, padding=0, stride=1, bias=False),
BatchNorm2d(256), nn.ReLU(inplace=False), SEModule(256, reduction=16))
self.alpha_fb = nn.Parameter(torch.ones(1))
def __init__(self, num_classes):
super(DecoderModule, self).__init__()
self.conv0 = nn.Sequential(
nn.Conv2d(512,
512,
kernel_size=3,
padding=1,
dilation=1,
bias=False), BatchNorm2d(512), nn.ReLU(inplace=False))
self.conv1 = nn.Sequential(
nn.Conv2d(512,
256,
kernel_size=3,
padding=1,
dilation=1,
bias=False), BatchNorm2d(256), nn.ReLU(inplace=False),
SEModule(256, reduction=16))
# self.conv2 = nn.Sequential(nn.Conv2d(256, 48, kernel_size=1, stride=1, padding=0, dilation=1, bias=False),
# BatchNorm2d(48), nn.ReLU(inplace=False))
#
# self.conv3 = nn.Sequential(nn.Conv2d(304, 256, kernel_size=1, padding=0, dilation=1, bias=False),
# BatchNorm2d(256), nn.ReLU(inplace=False),
# nn.Conv2d(256, 256, kernel_size=1, padding=0, dilation=1, bias=False),
# BatchNorm2d(256), nn.ReLU(inplace=False))
# self.conv4 = nn.Conv2d(256, num_classes, kernel_size=1, padding=0, dilation=1, bias=True)
self.alpha = nn.Parameter(torch.ones(1))
def __init__(self, fbody_cls):
super(FBodyDecoder, self).__init__()
self.conv0 = nn.Sequential(
nn.Conv2d(256,
48,
kernel_size=1,
stride=1,
padding=0,
dilation=1,
bias=False), BatchNorm2d(48), nn.ReLU(inplace=False))
self.conv1 = nn.Sequential(
nn.Conv2d(304, 256, kernel_size=3, padding=1, stride=1,
bias=False),
BatchNorm2d(256),
nn.ReLU(inplace=False),
nn.Conv2d(256, 256, kernel_size=1, padding=0, stride=1,
bias=False),
BatchNorm2d(256),
nn.ReLU(inplace=False),
SEModule(256, reduction=16),
)
self.project = nn.Conv2d(256,
fbody_cls,
kernel_size=1,
padding=0,
stride=1,
bias=True)
def __init__(self, in_dim, out_dim, scale):
super(MagicModule, self).__init__()
self.atte_branch = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=3,
padding=1,
dilation=1,
bias=True), InPlaceABNSync(out_dim),
SelfAttentionModule(in_dim=out_dim,
out_dim=out_dim,
key_dim=out_dim // 2,
value_dim=out_dim,
scale=scale))
# added
self.dilation_x = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_0 = nn.Sequential(
ContextContrastedModule(in_dim, out_dim, rate=6),
SEModule(out_dim, reduction=16))
self.dilation_1 = nn.Sequential(
ContextContrastedModule(in_dim, out_dim, rate=12),
SEModule(out_dim, reduction=16))
self.dilation_2 = nn.Sequential(
ContextContrastedModule(in_dim, out_dim, rate=18),
SEModule(out_dim, reduction=16))
self.dilation_3 = nn.Sequential(
ContextContrastedModule(in_dim, out_dim, rate=24),
SEModule(out_dim, reduction=16))
self.head_conv = nn.Sequential(
nn.Conv2d(out_dim * 6,
out_dim,
kernel_size=1,
padding=0,
bias=False), InPlaceABNSync(out_dim))
def __init__(self, hbody_cls):
super(AlphaHBDecoder, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(512, 256, kernel_size=3, padding=1, stride=1,
bias=False), BatchNorm2d(256), nn.ReLU(inplace=False),
nn.Conv2d(256, 256, kernel_size=1, padding=0, stride=1,
bias=False), BatchNorm2d(256), nn.ReLU(inplace=False),
SEModule(256, reduction=16),
nn.Conv2d(256,
hbody_cls,
kernel_size=1,
padding=0,
stride=1,
bias=True))
def __init__(self, in_dim, num_classes):
super(DecoderModule, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(in_dim,
256,
kernel_size=3,
padding=1,
stride=1,
bias=False), BatchNorm2d(256), nn.ReLU(inplace=False),
nn.Conv2d(256,
256,
kernel_size=3,
padding=1,
dilation=1,
bias=False), BatchNorm2d(256), nn.ReLU(inplace=False),
SEModule(256, reduction=16),
nn.Conv2d(256,
num_classes,
kernel_size=1,
padding=0,
dilation=1,
bias=True))
def __init__(self, in_dim, out_dim, scale=1):
super(ASPPModule, self).__init__()
self.gap = nn.Sequential(nn.AdaptiveAvgPool2d(1),
nn.Conv2d(in_dim, out_dim, 1, bias=False),
InPlaceABNSync(out_dim))
self.dilation_0 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_1 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
nn.Conv2d(out_dim,
out_dim,
kernel_size=3,
padding=6,
dilation=6,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_2 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
nn.Conv2d(out_dim,
out_dim,
kernel_size=3,
padding=12,
dilation=12,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_3 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
nn.Conv2d(out_dim,
out_dim,
kernel_size=3,
padding=18,
dilation=18,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.psaa_conv = nn.Sequential(
nn.Conv2d(in_dim + 5 * out_dim, out_dim, 1, padding=0, bias=False),
InPlaceABNSync(out_dim), nn.Conv2d(out_dim, 5, 1, bias=True),
nn.Sigmoid())
self.project = nn.Sequential(
nn.Conv2d(out_dim * 5,
out_dim,
kernel_size=1,
padding=0,
bias=False), InPlaceABNSync(out_dim))
def __init__(self, in_dim, out_dim):
super(ASPPModule2, self).__init__()
self.gap = nn.Sequential(nn.AdaptiveAvgPool2d(1),
nn.Conv2d(in_dim, out_dim, 1, bias=False),
InPlaceABNSync(out_dim))
self.dilation_0 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_1 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
nn.Conv2d(out_dim,
out_dim,
kernel_size=3,
padding=6,
dilation=6,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_2 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
nn.Conv2d(out_dim,
out_dim,
kernel_size=3,
padding=12,
dilation=12,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.dilation_3 = nn.Sequential(
nn.Conv2d(in_dim,
out_dim,
kernel_size=1,
padding=0,
dilation=1,
bias=False), InPlaceABNSync(out_dim),
nn.Conv2d(out_dim,
out_dim,
kernel_size=3,
padding=18,
dilation=18,
bias=False), InPlaceABNSync(out_dim),
SEModule(out_dim, reduction=16))
self.project = nn.Sequential(
nn.Conv2d(out_dim * 5,
out_dim,
kernel_size=1,
padding=0,
bias=False), InPlaceABNSync(out_dim))
self.pam0 = PAM_Module(in_dim=out_dim,
key_dim=out_dim // 8,
value_dim=out_dim,
out_dim=out_dim)
