unet简单实现

U-Net，主要是针对生物医学图片的分割

model_part

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


class DoubleConv(nn.Module):
    # Conv = > Batch_Norm = > ReLU = > Conv2d = > Batch_Norm = > ReLU
    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),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=0),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)

        )

    def forward(self, x):
        x = self.double_conv(x)
        return x


class Down(nn.Module):

    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.maxpool_conv = nn.Sequential(
            nn.MaxPool2d(2),
            DoubleConv(in_channels, out_channels)
        )

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


class Up(nn.Module):
    def __init__(self, in_channels, out_channels, bilinear=False):
        super().__init__()
        self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2)
        self.conv = DoubleConv(out_channels * 2, out_channels)

    def Cropsize(self, x1, x2):
        dix = (x2.size()[2] - x1.size()[2]) // 2
        diy = (x2.size()[3] - x1.size()[3]) // 2
        print('\n')
        print('dix:', dix)
        print('diy:', diy)
        return x2[:, :, dix:(dix + x1.size()[2]), diy:(diy + x1.size()[3])]

    def forward(self, x1, x2):
        # 四维batch, channel, height, width
        x1 = self.up(x1)
        crop = self.Cropsize(x1, x2)
        x = torch.cat([x1, crop], dim=1)  # channel上cat,
        print(x.size())
        x = self.conv(x)
        return x


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)

model

from unet.model_part import *


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.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, False)
        self.up2 = Up(512, 256, False)
        self.up3 = Up(256, 128, False)
        self.up4 = Up(128, 64, False)
        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)
        logits = self.outc(x)
        return logits


x = torch.rand(size=(2, 3, 572, 572))  # 电脑资源有限batch只能设小一些哈
unet = UNet(3, 10)
print(unet)
out = unet(x)