import torch import torch.nn as nn import torch.nn.functional as F class REBNCONV(nn.Module): def __init__(self,in_ch=3,out_ch=3,dirate=1): super(REBNCONV,self).__init__() self.conv_s1 = nn.Conv2d(in_ch,out_ch,3,padding=1*dirate,dilation=1*dirate) self.bn_s1 = nn.BatchNorm2d(out_ch) self.relu_s1 = nn.ReLU(inplace=True) def forward(self,x): hx = x xout = self.relu_s1(self.bn_s1(self.conv_s1(hx))) return xout ## upsample tensor 'src' to have the same spatial size with tensor 'tar' def _upsample_like(src,tar): src = F.upsample(src,size=tar.shape[2:],mode='bilinear') return src ### RSU-7 ### class RSU7(nn.Module):#UNet07DRES(nn.Module): def __init__(self, in_ch=3, mid_ch=12, out_ch=3): super(RSU7,self).__init__() self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) self.pool1 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool2 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool3 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool4 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool5 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=1) self.rebnconv7 = REBNCONV(mid_ch,mid_ch,dirate=2) self.rebnconv6d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) def forward(self,x): hx = x hxin = self.rebnconvin(hx) hx1 = self.rebnconv1(hxin) hx = self.pool1(hx1) hx2 = self.rebnconv2(hx) hx = self.pool2(hx2) hx3 = self.rebnconv3(hx) hx = self.pool3(hx3) hx4 = self.rebnconv4(hx) hx = self.pool4(hx4) hx5 = self.rebnconv5(hx) hx = self.pool5(hx5) hx6 = self.rebnconv6(hx) hx7 = self.rebnconv7(hx6) hx6d = self.rebnconv6d(torch.cat((hx7,hx6),1)) hx6dup = _upsample_like(hx6d,hx5) hx5d = self.rebnconv5d(torch.cat((hx6dup,hx5),1)) hx5dup = _upsample_like(hx5d,hx4) hx4d = self.rebnconv4d(torch.cat((hx5dup,hx4),1)) hx4dup = _upsample_like(hx4d,hx3) hx3d = self.rebnconv3d(torch.cat((hx4dup,hx3),1)) hx3dup = _upsample_like(hx3d,hx2) hx2d = self.rebnconv2d(torch.cat((hx3dup,hx2),1)) hx2dup = _upsample_like(hx2d,hx1) hx1d = self.rebnconv1d(torch.cat((hx2dup,hx1),1)) return hx1d + hxin ### RSU-6 ### class RSU6(nn.Module):#UNet06DRES(nn.Module): def __init__(self, in_ch=3, mid_ch=12, out_ch=3): super(RSU6,self).__init__() self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) self.pool1 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool2 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool3 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool4 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=2) self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) def forward(self,x): hx = x hxin = self.rebnconvin(hx) hx1 = self.rebnconv1(hxin) hx = self.pool1(hx1) hx2 = self.rebnconv2(hx) hx = self.pool2(hx2) hx3 = self.rebnconv3(hx) hx = self.pool3(hx3) hx4 = self.rebnconv4(hx) hx = self.pool4(hx4) hx5 = self.rebnconv5(hx) hx6 = self.rebnconv6(hx5) hx5d = self.rebnconv5d(torch.cat((hx6,hx5),1)) hx5dup = _upsample_like(hx5d,hx4) hx4d = self.rebnconv4d(torch.cat((hx5dup,hx4),1)) hx4dup = _upsample_like(hx4d,hx3) hx3d = self.rebnconv3d(torch.cat((hx4dup,hx3),1)) hx3dup = _upsample_like(hx3d,hx2) hx2d = self.rebnconv2d(torch.cat((hx3dup,hx2),1)) hx2dup = _upsample_like(hx2d,hx1) hx1d = self.rebnconv1d(torch.cat((hx2dup,hx1),1)) return hx1d + hxin ### RSU-5 ### class RSU5(nn.Module):#UNet05DRES(nn.Module): def __init__(self, in_ch=3, mid_ch=12, out_ch=3): super(RSU5,self).__init__() self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) self.pool1 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool2 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool3 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=2) self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) def forward(self,x): hx = x hxin = self.rebnconvin(hx) hx1 = self.rebnconv1(hxin) hx = self.pool1(hx1) hx2 = self.rebnconv2(hx) hx = self.pool2(hx2) hx3 = self.rebnconv3(hx) hx = self.pool3(hx3) hx4 = self.rebnconv4(hx) hx5 = self.rebnconv5(hx4) hx4d = self.rebnconv4d(torch.cat((hx5,hx4),1)) hx4dup = _upsample_like(hx4d,hx3) hx3d = self.rebnconv3d(torch.cat((hx4dup,hx3),1)) hx3dup = _upsample_like(hx3d,hx2) hx2d = self.rebnconv2d(torch.cat((hx3dup,hx2),1)) hx2dup = _upsample_like(hx2d,hx1) hx1d = self.rebnconv1d(torch.cat((hx2dup,hx1),1)) return hx1d + hxin ### RSU-4 ### class RSU4(nn.Module):#UNet04DRES(nn.Module): def __init__(self, in_ch=3, mid_ch=12, out_ch=3): super(RSU4,self).__init__() self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) self.pool1 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) self.pool2 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=2) self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) def forward(self,x): hx = x hxin = self.rebnconvin(hx) hx1 = self.rebnconv1(hxin) hx = self.pool1(hx1) hx2 = self.rebnconv2(hx) hx = self.pool2(hx2) hx3 = self.rebnconv3(hx) hx4 = self.rebnconv4(hx3) hx3d = self.rebnconv3d(torch.cat((hx4,hx3),1)) hx3dup = _upsample_like(hx3d,hx2) hx2d = self.rebnconv2d(torch.cat((hx3dup,hx2),1)) hx2dup = _upsample_like(hx2d,hx1) hx1d = self.rebnconv1d(torch.cat((hx2dup,hx1),1)) return hx1d + hxin ### RSU-4F ### class RSU4F(nn.Module):#UNet04FRES(nn.Module): def __init__(self, in_ch=3, mid_ch=12, out_ch=3): super(RSU4F,self).__init__() self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=2) self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=4) self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=8) self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=4) self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=2) self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) def forward(self,x): hx = x hxin = self.rebnconvin(hx) hx1 = self.rebnconv1(hxin) hx2 = self.rebnconv2(hx1) hx3 = self.rebnconv3(hx2) hx4 = self.rebnconv4(hx3) hx3d = self.rebnconv3d(torch.cat((hx4,hx3),1)) hx2d = self.rebnconv2d(torch.cat((hx3d,hx2),1)) hx1d = self.rebnconv1d(torch.cat((hx2d,hx1),1)) return hx1d + hxin from faceseg.tma import SequenceConv, MemoryModule ##### U^2-Net #### class U2NET(nn.Module): def __init__(self, in_ch=3, out_ch=1): super(U2NET, self).__init__() self.stage1 = RSU7(in_ch,32,64) self.pool12 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.stage2 = RSU6(64,32,128) self.pool23 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.stage3 = RSU5(128,64,256) self.pool34 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.stage4 = RSU4(256,128,512) self.pool45 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.stage5 = RSU4F(512,256,512) self.pool56 = nn.MaxPool2d(2,stride=2,ceil_mode=True) self.stage6 = RSU4F(512,256,512) # decoder self.stage5d = RSU4F(1024,256,512) self.stage4d = RSU4(1024,128,256) self.stage3d = RSU5(512,64,128) self.stage2d = RSU6(256,32,64) self.stage1d = RSU7(128,16,64) self.side1 = nn.Conv2d(64,out_ch,3,padding=1) self.side2 = nn.Conv2d(64,out_ch,3,padding=1) self.side3 = nn.Conv2d(128,out_ch,3,padding=1) self.side4 = nn.Conv2d(256,out_ch,3,padding=1) self.side5 = nn.Conv2d(512,out_ch,3,padding=1) self.side6 = nn.Conv2d(512,out_ch,3,padding=1) self.outconv = nn.Conv2d(6*out_ch,out_ch,1) self.in_channels = 512 key_channels = 128 value_channels = 512 self.sequence_num = sequence_num = 2 self.memory_key_conv = nn.Sequential( SequenceConv(self.in_channels, key_channels, 1, sequence_num), SequenceConv(key_channels, key_channels, 3, sequence_num) ) self.memory_value_conv = nn.Sequential( SequenceConv(self.in_channels, value_channels, 1, sequence_num), SequenceConv(value_channels, value_channels, 3, sequence_num) ) self.query_key_conv = nn.Sequential( nn.Sequential( nn.Conv2d(self.in_channels, key_channels, 1, 1, 0, bias=False), nn.BatchNorm2d(key_channels), nn.ReLU() ), nn.Sequential( nn.Conv2d(key_channels, key_channels, 3, 1, 1, bias=False), nn.BatchNorm2d(key_channels), nn.ReLU() ), ) self.query_value_conv = nn.Sequential( nn.Sequential( nn.Conv2d(self.in_channels, value_channels, 1, 1, 0, bias=False), nn.BatchNorm2d(value_channels), nn.ReLU() ), nn.Sequential( nn.Conv2d(value_channels, value_channels, 3, 1, 1, bias=False), nn.BatchNorm2d(value_channels), nn.ReLU() ), ) self.memory_module = MemoryModule(matmul_norm=False) self.bottleneck = nn.Sequential( nn.Conv2d(value_channels * 2, self.in_channels, 3, 1, 1, bias=False), nn.BatchNorm2d(value_channels), nn.ReLU() ) self.is_train = True def extract_feature(self, x): hx = x # stage 1 hx1 = self.stage1(hx) hx = self.pool12(hx1) # stage 2 hx2 = self.stage2(hx) hx = self.pool23(hx2) # stage 3 hx3 = self.stage3(hx) hx = self.pool34(hx3) # stage 4 hx4 = self.stage4(hx) hx = self.pool45(hx4) # stage 5 hx5 = self.stage5(hx) hx = self.pool56(hx5) # stage 6 hx6 = self.stage6(hx) return hx1, hx2, hx3, hx4, hx5, hx6 def decoder(self, hx1, hx2, hx3, hx4, hx5, hx6): hx6up = _upsample_like(hx6, hx5) # -------------------- decoder -------------------- hx5d = self.stage5d(torch.cat((hx6up, hx5), 1)) hx5dup = _upsample_like(hx5d, hx4) hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1)) hx4dup = _upsample_like(hx4d, hx3) hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1)) hx3dup = _upsample_like(hx3d, hx2) hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1)) hx2dup = _upsample_like(hx2d, hx1) hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1)) return hx1d, hx2d, hx3d, hx4d, hx5d def side_output(self, hx1d, hx2d, hx3d, hx4d, hx5d, hx6): # side output d1 = self.side1(hx1d) d2 = self.side2(hx2d) d2 = _upsample_like(d2, d1) d3 = self.side3(hx3d) d3 = _upsample_like(d3, d1) d4 = self.side4(hx4d) d4 = _upsample_like(d4, d1) d5 = self.side5(hx5d) d5 = _upsample_like(d5, d1) d6 = self.side6(hx6) d6 = _upsample_like(d6, d1) d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1)) return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) def forward(self, x, memory_sequence=None): if self.is_train: hx1, hx2, hx3, hx4, hx5, hx6 = self.extract_feature(x) if memory_sequence is None: memory_hx6 = [hx6 for _ in range(self.sequence_num)] else: memory_hx6 = [] for single_memory in memory_sequence: _, _, _, _, _, hx6 = self.extract_feature(single_memory) memory_hx6.append(hx6) memory_hx6 = [mhx6.unsqueeze(0) for mhx6 in memory_hx6] # T, BxCxHxW memory_hx6 = torch.cat(memory_hx6, dim=0) memory_keys = self.memory_key_conv(memory_hx6) memory_values = self.memory_value_conv(memory_hx6) query_key = self.query_key_conv(hx6) query_value = self.query_value_conv(hx6) merge_hx6 = self.memory_module(memory_keys, memory_values, query_key, query_value) merge_hx6 = self.bottleneck(merge_hx6) hx1d, hx2d, hx3d, hx4d, hx5d = self.decoder(hx1, hx2, hx3, hx4, hx5, merge_hx6) return self.side_output(hx1d, hx2d, hx3d, hx4d, hx5d, hx6) else: return self.test(x) def test(self, x): with torch.no_grad(): hx1, hx2, hx3, hx4, hx5, hx6 = self.extract_feature(x) memory_hx6 = [hx6 for _ in range(self.sequence_num)] memory_hx6 = [mhx6.unsqueeze(0) for mhx6 in memory_hx6] # T, BxCxHxW memory_hx6 = torch.cat(memory_hx6, dim=0) memory_keys = self.memory_key_conv(memory_hx6) memory_values = self.memory_value_conv(memory_hx6) query_key = self.query_key_conv(hx6) query_value = self.query_value_conv(hx6) merge_hx6 = self.memory_module(memory_keys, memory_values, query_key, query_value) merge_hx6 = self.bottleneck(merge_hx6) hx1d, hx2d, hx3d, hx4d, hx5d = self.decoder(hx1, hx2, hx3, hx4, hx5, merge_hx6) mask, _, _, _, _, _, _ = self.side_output(hx1d, hx2d, hx3d, hx4d, hx5d, hx6) return mask # # ### U^2-Net small ### # class U2NETP(nn.Module): # # def __init__(self,in_ch=3,out_ch=1): # super(U2NETP,self).__init__() # # self.stage1 = RSU7(in_ch,16,64) # self.pool12 = nn.MaxPool2d(2,stride=2,ceil_mode=True) # # self.stage2 = RSU6(64,16,64) # self.pool23 = nn.MaxPool2d(2,stride=2,ceil_mode=True) # # self.stage3 = RSU5(64,16,64) # self.pool34 = nn.MaxPool2d(2,stride=2,ceil_mode=True) # # self.stage4 = RSU4(64,16,64) # self.pool45 = nn.MaxPool2d(2,stride=2,ceil_mode=True) # # self.stage5 = RSU4F(64,16,64) # self.pool56 = nn.MaxPool2d(2,stride=2,ceil_mode=True) # # self.stage6 = RSU4F(64,16,64) # # # decoder # self.stage5d = RSU4F(128,16,64) # self.stage4d = RSU4(128,16,64) # self.stage3d = RSU5(128,16,64) # self.stage2d = RSU6(128,16,64) # self.stage1d = RSU7(128,16,64) # # self.side1 = nn.Conv2d(64,out_ch,3,padding=1) # self.side2 = nn.Conv2d(64,out_ch,3,padding=1) # self.side3 = nn.Conv2d(64,out_ch,3,padding=1) # self.side4 = nn.Conv2d(64,out_ch,3,padding=1) # self.side5 = nn.Conv2d(64,out_ch,3,padding=1) # self.side6 = nn.Conv2d(64,out_ch,3,padding=1) # # self.outconv = nn.Conv2d(6*out_ch,out_ch,1) # # def forward(self,x): # # hx = x # # #stage 1 # hx1 = self.stage1(hx) # hx = self.pool12(hx1) # # #stage 2 # hx2 = self.stage2(hx) # hx = self.pool23(hx2) # # #stage 3 # hx3 = self.stage3(hx) # hx = self.pool34(hx3) # # #stage 4 # hx4 = self.stage4(hx) # hx = self.pool45(hx4) # # #stage 5 # hx5 = self.stage5(hx) # hx = self.pool56(hx5) # # #stage 6 # hx6 = self.stage6(hx) # hx6up = _upsample_like(hx6,hx5) # # #decoder # hx5d = self.stage5d(torch.cat((hx6up,hx5),1)) # hx5dup = _upsample_like(hx5d,hx4) # # hx4d = self.stage4d(torch.cat((hx5dup,hx4),1)) # hx4dup = _upsample_like(hx4d,hx3) # # hx3d = self.stage3d(torch.cat((hx4dup,hx3),1)) # hx3dup = _upsample_like(hx3d,hx2) # # hx2d = self.stage2d(torch.cat((hx3dup,hx2),1)) # hx2dup = _upsample_like(hx2d,hx1) # # hx1d = self.stage1d(torch.cat((hx2dup,hx1),1)) # # # #side output # d1 = self.side1(hx1d) # # d2 = self.side2(hx2d) # d2 = _upsample_like(d2,d1) # # d3 = self.side3(hx3d) # d3 = _upsample_like(d3,d1) # # d4 = self.side4(hx4d) # d4 = _upsample_like(d4,d1) # # d5 = self.side5(hx5d) # d5 = _upsample_like(d5,d1) # # d6 = self.side6(hx6) # d6 = _upsample_like(d6,d1) # # d0 = self.outconv(torch.cat((d1,d2,d3,d4,d5,d6),1)) # # return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6)