Unet

Unet

概述

UNet是遵循FCN的原理，并进行了相应的改进，使其适应小样本的简单分割问题。

网络架构

代码

• 导入依赖

import torch
from torch import nn as nn
import torch.nn.functional as F

• 下采样过程每一层两次卷积

class DoubleConv(nn.Module):
    """(convolution => [BN] => ReLU) * 2"""
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=0),#可能为了保持图像大小不变 我们会修改padding=1
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True), #对变量值可以直接替换，减少内存使用
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=0),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )
    def forward(self, x):
        return self.double_conv(x)

• 下采样

class Down(nn.Module):
    """Downscaling with maxpool then double conv"""
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.maxpool_conv = nn.Sequential(
            nn.MaxPool2d(2),   #最大池化层，下采样
            DoubleConv(in_channels, out_channels)
        )
    def forward(self, x):
        return self.maxpool_conv(x)

• 上采样

class Up(nn.Module):
    """Upscaling then double conv"""
    def __init__(self, in_channels, out_channels, bilinear=True):
        super().__init__()
        # if bilinear, use the normal convolutions to reduce the number of channels
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
        else:
            self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2)

        self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        x1 = self.up(x1)
        # input is CHW
        diffY = torch.tensor([x2.size()[2] - x1.size()[2]])
        diffX = torch.tensor([x2.size()[3] - x1.size()[3]])
        print(diffX.shape)
        print(diffY.shape)
        #x1是上采样的数据，x2是进行特征融合的数据
       x1 = F.pad(x1, [torch.div(diffX,2,rounding_mode='floor'),diffX - torch.div(diffX,2,rounding_mode='floor')
            ,torch.div(diffY,2,rounding_mode='floor'), diffY - torch.div(diffY,2,rounding_mode='floor')]) #对较小的feature_map进行填充后才能进行合并
        print(x1.shape)
        x = torch.cat([x2, x1], dim=1)  #在通道维进行合并
        return self.conv(x)

• 最后一层的通道数变换

class OutConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(OutConv, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)

    def forward(self, x):
        return self.conv(x)

• 整体网络架构

class UNet(nn.Module):
    def __init__(self, n_channels, n_classes, bilinear=False):
        super(UNet, self).__init__()
        self.n_channels = n_channels
        self.n_classes = n_classes
        self.bilinear = bilinear

        self.inc = DoubleConv(n_channels, 64)
        self.down1 = Down(64, 128)
        self.down2 = Down(128, 256)
        self.down3 = Down(256, 512)
        self.down4 = Down(512, 1024)
        self.up1 = Up(1024, 512, bilinear)
        self.up2 = Up(512, 256, bilinear)
        self.up3 = Up(256, 128, bilinear)
        self.up4 = Up(128, 64, bilinear)
        self.outc = OutConv(64, n_classes)

    def forward(self, x):
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x3 = self.down2(x2)
        x4 = self.down3(x3)
        x5 = self.down4(x4)
        x = self.up1(x5, x4)
        x = self.up2(x, x3)
        x = self.up3(x, x2)
        x = self.up4(x, x1)
        net = self.outc(x)
        return net

net = UNet(n_channels=3, n_classes=1)
print(net)

输出：

UNet(
  (inc): DoubleConv(
    (double_conv): Sequential(
      (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1))
      (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
      (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))
      (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (5): ReLU(inplace=True)
    )
  )
  (down1): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1))
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1))
          (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down2): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1))
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
          (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down3): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1))
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1))
          (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down4): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1))
          (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
          (4): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (up1): Up(
    (up): ConvTranspose2d(1024, 512, kernel_size=(2, 2), stride=(2, 2))
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1))
        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1))
        (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up2): Up(
    (up): ConvTranspose2d(512, 256, kernel_size=(2, 2), stride=(2, 2))
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1))
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1))
        (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up3): Up(
    (up): ConvTranspose2d(256, 128, kernel_size=(2, 2), stride=(2, 2))
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1))
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1))
        (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up4): Up(
    (up): ConvTranspose2d(128, 64, kernel_size=(2, 2), stride=(2, 2))
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1))
        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1))
        (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (outc): OutConv(
    (conv): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
  )
)

（1）UNet语义分割网络

（2）UNet模型训练