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 # Border Network class RRB(nn.Module): def __init__(self, in_ch, out_ch): super(RRB, self).__init__() self.conv1 = nn.Conv2d(in_ch, out_ch, kernel_size=1, stride=1, padding=0) self.conv2 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) self.relu = nn.ReLU() self.bn = nn.BatchNorm2d(out_ch) self.conv3 = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1) def forward(self, x): x = self.conv1(x) res = self.conv2(x) res = self.bn(res) res = self.relu(res) res = self.conv3(res) return self.relu(x + res) # CBAM attention class CBAMLayer(nn.Module): def __init__(self, channel, reduction=16, spatial_kernel=7): super(CBAMLayer, self).__init__() # channel attention 压缩H,W为1 self.max_pool = nn.AdaptiveMaxPool2d(1) self.avg_pool = nn.AdaptiveAvgPool2d(1) # shared MLP self.mlp = nn.Sequential( # Conv2d比Linear方便操作 # nn.Linear(channel, channel // reduction, bias=False) nn.Conv2d(channel, channel // reduction, 1, bias=False), # inplace=True直接替换，节省内存 nn.ReLU(inplace=True), # nn.Linear(channel // reduction, channel,bias=False) nn.Conv2d(channel // reduction, channel, 1, bias=False) ) # spatial attention self.conv = nn.Conv2d(2, 1, kernel_size=spatial_kernel, padding=spatial_kernel // 2, bias=False) self.sigmoid = nn.Sigmoid() def forward(self, x): max_out = self.mlp(self.max_pool(x)) avg_out = self.mlp(self.avg_pool(x)) channel_out = self.sigmoid(max_out + avg_out) x = channel_out * x max_out, _ = torch.max(x, dim=1, keepdim=True) avg_out = torch.mean(x, dim=1, keepdim=True) spatial_out = self.sigmoid(self.conv(torch.cat([max_out, avg_out], dim=1))) x = spatial_out * x return x ## 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') # old version torch src = F.upsample(src, size=tar.shape[2:], mode='bilinear', align_corners=True) 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 ##### 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) ################## self.upsample = nn.Upsample(scale_factor=2, mode="bilinear") self.upsample_4 = nn.Upsample(scale_factor=4, mode="bilinear") self.upsample_8 = nn.Upsample(scale_factor=8, mode="bilinear") self.upsample_16 = nn.Upsample(scale_factor=16, mode="bilinear") self.upsample_32 = nn.Upsample(scale_factor=32, mode="bilinear") self.rrb_db_1 = RRB(64, 1) self.rrb_db_2 = RRB(128, 1) self.rrb_db_3 = RRB(256, 1) self.rrb_db_4 = RRB(512, 1) self.rrb_db_5 = RRB(512, 1) self.rrb_db_6 = RRB(512, 1) self.rrb_trans_1 = RRB(1,1) self.rrb_trans_2 = RRB(1,1) self.rrb_trans_3 = RRB(1,1) self.rrb_trans_4 = RRB(1,1) self.rrb_trans_5 = RRB(1,1) ################################################# # CBAM attention self.sa1 = CBAMLayer(64) self.sa2 = CBAMLayer(128) self.sa3 = CBAMLayer(256) self.sa4 = CBAMLayer(512) self.sa5 = CBAMLayer(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.side7 = nn.Conv2d(1, out_ch, 3, padding=1) self.outconv = nn.Conv2d(7 * 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) res1 = self.rrb_db_1(hx1) res1 = self.rrb_trans_1(res1 + self.upsample(self.rrb_db_2(hx2))) res1 = self.rrb_trans_2(res1 + self.upsample_4(self.rrb_db_3(hx3))) res1 = self.rrb_trans_3(res1 + self.upsample_8(self.rrb_db_4(hx4))) res1 = self.rrb_trans_4(res1 + self.upsample_16(self.rrb_db_5(hx5))) res1 = self.rrb_trans_5(res1 + self.upsample_32(self.rrb_db_6(hx6))) # -------------------- decoder -------------------- sa5 = self.sa5(hx5) hx5d = self.stage5d(torch.cat((hx6up, sa5), 1)) hx5dup = _upsample_like(hx5d, hx4) sa4 = self.sa4(hx4) hx4d = self.stage4d(torch.cat((hx5dup, sa4), 1)) hx4dup = _upsample_like(hx4d, hx3) sa3 = self.sa3(hx3) hx3d = self.stage3d(torch.cat((hx4dup, sa3), 1)) hx3dup = _upsample_like(hx3d, hx2) sa2 = self.sa2(hx2) hx2d = self.stage2d(torch.cat((hx3dup, sa2), 1)) hx2dup = _upsample_like(hx2d, hx1) sa1 = self.sa1(hx1) hx1d = self.stage1d(torch.cat((hx2dup, sa1), 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) d7 = self.side7(res1) d7 = _upsample_like(d7, d1) d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6, d7), 1)) # return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6), F.sigmoid(d7) return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(d4), torch.sigmoid(d5), torch.sigmoid(d6), torch.sigmoid(d7) ### 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) ################## self.upsample = nn.Upsample(scale_factor=2, mode="bilinear") self.upsample_4 = nn.Upsample(scale_factor=4, mode="bilinear") self.upsample_8 = nn.Upsample(scale_factor=8, mode="bilinear") self.upsample_16 = nn.Upsample(scale_factor=16, mode="bilinear") self.upsample_32 = nn.Upsample(scale_factor=32, mode="bilinear") self.rrb_db_1 = RRB(64, 1) self.rrb_db_2 = RRB(64, 1) self.rrb_db_3 = RRB(64, 1) self.rrb_db_4 = RRB(64, 1) self.rrb_db_5 = RRB(64, 1) self.rrb_db_6 = RRB(64, 1) self.rrb_trans_1 = RRB(1,1) self.rrb_trans_2 = RRB(1,1) self.rrb_trans_3 = RRB(1,1) self.rrb_trans_4 = RRB(1,1) self.rrb_trans_5 = RRB(1,1) ################################################# # CBAM attention self.sa1 = CBAMLayer(64) self.sa2 = CBAMLayer(64) self.sa3 = CBAMLayer(64) self.sa4 = CBAMLayer(64) self.sa5 = CBAMLayer(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.side7 = nn.Conv2d(1, out_ch, 3, padding=1) self.outconv = nn.Conv2d(7 * 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) res1 = self.rrb_db_1(hx1) res1 = self.rrb_trans_1(res1 + self.upsample(self.rrb_db_2(hx2))) res1 = self.rrb_trans_2(res1 + self.upsample_4(self.rrb_db_3(hx3))) res1 = self.rrb_trans_3(res1 + self.upsample_8(self.rrb_db_4(hx4))) res1 = self.rrb_trans_4(res1 + self.upsample_16(self.rrb_db_5(hx5))) res1 = self.rrb_trans_5(res1 + self.upsample_32(self.rrb_db_6(hx6))) # decoder sa5 = self.sa5(hx5) hx5d = self.stage5d(torch.cat((hx6up, sa5), 1)) hx5dup = _upsample_like(hx5d, hx4) sa4 = self.sa4(hx4) hx4d = self.stage4d(torch.cat((hx5dup, sa4), 1)) hx4dup = _upsample_like(hx4d, hx3) sa3 = self.sa3(hx3) hx3d = self.stage3d(torch.cat((hx4dup, sa3), 1)) hx3dup = _upsample_like(hx3d, hx2) sa2 = self.sa2(hx2) hx2d = self.stage2d(torch.cat((hx3dup, sa2), 1)) hx2dup = _upsample_like(hx2d, hx1) sa1 = self.sa1(hx1) hx1d = self.stage1d(torch.cat((hx2dup, sa1), 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) d7 = self.side7(res1) d7 = _upsample_like(d7, d1) d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6, d7), 1)) # return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6), F.sigmoid(d7) return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(d4), torch.sigmoid(d5), torch.sigmoid(d6), torch.sigmoid(d7)