写一个基于self attention 的 unet模型程序

以下是一个基于self attention的unet模型的程序：

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

class SelfAttentionBlock(nn.Module):
    def __init__(self, in_channels):
        super(SelfAttentionBlock, self).__init__()
        self.query_conv = nn.Conv2d(in_channels, in_channels // 8, kernel_size=1)
        self.key_conv = nn.Conv2d(in_channels, in_channels // 8, kernel_size=1)
        self.value_conv = nn.Conv2d(in_channels, in_channels, kernel_size=1)
        self.gamma = nn.Parameter(torch.zeros(1))

    def forward(self, x):
        batch_size, C, H, W = x.size()
        proj_query = self.query_conv(x).view(batch_size, -1, H * W).permute(0, 2, 1)
        proj_key = self.key_conv(x).view(batch_size, -1, H * W)
        energy = torch.bmm(proj_query, proj_key)
        attention = F.softmax(energy, dim=-1)
        proj_value = self.value_conv(x).view(batch_size, -1, H * W)
        out = torch.bmm(proj_value, attention.permute(0, 2, 1))
        out = out.view(batch_size, C, H, W)
        out = self.gamma * out + x
        return out

class DoubleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(DoubleConv, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

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

class Up(nn.Module):
    def __init__(self, in_channels, out_channels, bilinear=True):
        super(Up, self).__init__()
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
        else:
            self.up = nn.ConvTranspose2d(in_channels // 2, in_channels // 2, kernel_size=2, stride=2)
        self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        x1 = self.up(x1)
        diffY = x2.size()[2] - x1.size()[2]
        diffX = x2.size()[3] - x1.size()[3]

        x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
                        diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1)
        x = self.conv(x)
        return x

class UNet(nn.Module):
    def __init__(self, n_channels, n_classes, bilinear=True):
        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 = DoubleConv(64, 128)
        self.down2 = DoubleConv(128, 256)
        self.down3 = DoubleConv(256, 512)
        self.down4 = DoubleConv(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 = nn.Conv2d(64, n_classes, kernel_size=1)

        self.sa1 = SelfAttentionBlock(64)
        self.sa2 = SelfAttentionBlock(128)
        self.sa3 = SelfAttentionBlock(256)
        self.sa4 = SelfAttentionBlock(512)

    def forward(self, x):
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x2 = self.sa1(x2)
        x3 = self.down2(x2)
        x3 = self.sa2(x3)
        x4 = self.down3(x3)
        x4 = self.sa3(x4)
        x5 = self.down4(x4)
        x5 = self.sa4(x5)
        x = self.up1(x5, x4)
        x = self.up2(x, x3)
        x = self.up3(x, x2)
        x = self.up4(x, x1)
        x = self.outc(x)
        return x

希望这个程序能够帮助你！