【Unet系列】
- 电脑硬件
- 2025-08-18 00:15:02
tianfeng.space/1947.html
前言概念 图像分割分割任务就是在原始图像中逐像素的找到你需要的家伙!
语义分割就是把每个像素都打上标签（这个像素点是人，树，背景等）
（语义分割只区分类别，不区分类别中具体单位）
实例分割实例分割不光要区别类别，还要区分类别中每一个个体
损失函数：逐像素的交叉熵：还经常需要考虑样本均衡问题，交叉熵损失函数公式如下：
Focal loss：样本也由难易之分，就跟玩游戏一样，难度越高的BOSS奖励越高
Gamma通常设置为2，例如预测正样本概率0.95，如果预测正样本概率0.4， （相当于样本的难易权值）
（再结合样本数量的权值就是Focal Loss）
IOU计算多分类任务时：iou_dog = 801 / true_dog + predict_dog - 801
MIOU指标： MIOU就是计算所有类别的平均值，一般当作分割任务评估指标
Unet整体结构：概述就是编码解码过程；简单但是很实用，应用广；起初是做医学方向，现在也是
Unet++整体网络结构：特征融合，拼接更全面；其实跟densenet思想一致；把能拼能凑的特征全用上
Deep Supervision ：多输出损失；由多个位置计算，再更新
容易剪枝：可以根据速度要求来快速完成剪枝；训练的时候同样会用到L4，效果还不错
U²net代码 论文
听名字知道就是把Unet中每个stage再变成一个Unet，这样就嵌套了一个Unet变成U²net；
输出为解码器各个阶段输出再拼接，经过一次卷积输出
现有卷积块和我们提出的残差U形块RSU的说明：（a）普通卷积块PLN，（b）残差类块RES，（c）密集类块DSE，（d）启始类块INC和（e）我们的残差U型块RSU
残差块与我们的RSU的比较
就作者展示的效果而言，出奇的不错，有兴趣去代码界面看看，使用也很简单，下面展示一些
代码结构放最后；有兴趣看看
#U²net结构；387行forward开始 import torch import torch.nn as nn from torchvision import models 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): print(x.shape) hx = x hxin = self.rebnconvin(hx) print(hxin.shape) hx1 = self.rebnconv1(hxin) print(hx1.shape) hx = self.pool1(hx1) print(hx.shape) hx2 = self.rebnconv2(hx) print(hx2.shape) hx = self.pool2(hx2) print(hx.shape) hx3 = self.rebnconv3(hx) print(hx3.shape) hx = self.pool3(hx3) print(hx.shape) hx4 = self.rebnconv4(hx) print(hx4.shape) hx = self.pool4(hx4) print(hx.shape) hx5 = self.rebnconv5(hx) print(hx5.shape) hx = self.pool5(hx5) print(hx.shape) hx6 = self.rebnconv6(hx) print(hx6.shape) hx7 = self.rebnconv7(hx6) print(hx7.shape) hx6d = self.rebnconv6d(torch.cat((hx7,hx6),1)) print(hx6d.shape) hx6dup = _upsample_like(hx6d,hx5) print(hx6dup.shape) hx5d = self.rebnconv5d(torch.cat((hx6dup,hx5),1)) print(hx5d.shape) hx5dup = _upsample_like(hx5d,hx4) print(hx5dup.shape) hx4d = self.rebnconv4d(torch.cat((hx5dup,hx4),1)) print(hx4d.shape) hx4dup = _upsample_like(hx4d,hx3) print(hx4dup.shape) hx3d = self.rebnconv3d(torch.cat((hx4dup,hx3),1)) print(hx3d.shape) hx3dup = _upsample_like(hx3d,hx2) print(hx3dup.shape) hx2d = self.rebnconv2d(torch.cat((hx3dup,hx2),1)) print(hx2d.shape) hx2dup = _upsample_like(hx2d,hx1) print(hx2dup.shape) hx1d = self.rebnconv1d(torch.cat((hx2dup,hx1),1)) print(hx1d.shape) 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) print(hxin.shape) hx1 = self.rebnconv1(hxin) print(hx1.shape) hx2 = self.rebnconv2(hx1) print(hx2.shape) hx3 = self.rebnconv3(hx2) print(hx3.shape) hx4 = self.rebnconv4(hx3) print(hx4.shape) hx3d = self.rebnconv3d(torch.cat((hx4,hx3),1)) print(hx3d.shape) hx2d = self.rebnconv2d(torch.cat((hx3d,hx2),1)) print(hx2d.shape) hx1d = self.rebnconv1d(torch.cat((hx2d,hx1),1)) print(hx1d.shape) 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) # 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,1) def forward(self,x): print(x.shape) hx = x #stage 1 hx1 = self.stage1(hx) print(hx1.shape) hx = self.pool12(hx1) print(hx.shape) #stage 2 hx2 = self.stage2(hx) print(hx2.shape) hx = self.pool23(hx2) print(hx.shape) #stage 3 hx3 = self.stage3(hx) print(hx3.shape) hx = self.pool34(hx3) print(hx.shape) #stage 4 hx4 = self.stage4(hx) print(hx4.shape) hx = self.pool45(hx4) print(hx.shape) #stage 5 hx5 = self.stage5(hx) print(hx5.shape) hx = self.pool56(hx5) print(hx.shape) #stage 6 hx6 = self.stage6(hx) print(hx6.shape) hx6up = _upsample_like(hx6,hx5) print(hx6up.shape) #-------------------- decoder -------------------- hx5d = self.stage5d(torch.cat((hx6up,hx5),1)) print(hx5d.shape) hx5dup = _upsample_like(hx5d,hx4) print(hx5dup.shape) hx4d = self.stage4d(torch.cat((hx5dup,hx4),1)) print(hx4d.shape) hx4dup = _upsample_like(hx4d,hx3) print(hx4dup.shape) hx3d = self.stage3d(torch.cat((hx4dup,hx3),1)) print(hx3d.shape) hx3dup = _upsample_like(hx3d,hx2) print(hx3dup.shape) hx2d = self.stage2d(torch.cat((hx3dup,hx2),1)) print(hx2d.shape) hx2dup = _upsample_like(hx2d,hx1) print(hx2dup.shape) hx1d = self.stage1d(torch.cat((hx2dup,hx1),1)) print(hx1d.shape) #side output d1 = self.side1(hx1d) print(d1.shape) d2 = self.side2(hx2d) print(d2.shape) d2 = _upsample_like(d2,d1) print(d2.shape) d3 = self.side3(hx3d) print(d3.shape) d3 = _upsample_like(d3,d1) print(d3.shape) d4 = self.side4(hx4d) print(d4.shape) d4 = _upsample_like(d4,d1) print(d4.shape) d5 = self.side5(hx5d) print(d5.shape) d5 = _upsample_like(d5,d1) print(d5.shape) d6 = self.side6(hx6) print(d6.shape) d6 = _upsample_like(d6,d1) print(d6.shape) d0 = self.outconv(torch.cat((d1,d2,d3,d4,d5,d6),1)) print(d0.shape) return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) ### 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,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)
