pytorch搭建Unet网络结构

advancezhang

已于 2022-01-31 21:51:26 修改

阅读量523

点赞数 1

CC 4.0 BY-SA版权

分类专栏：人工智能文章标签：网络深度学习 pytorch

于 2022-01-27 21:33:09 首次发布

本文链接：https://blog.youkuaiyun.com/advancezhang/article/details/122723918

人工智能专栏收录该内容

3 篇文章

订阅专栏

本文介绍如何使用PyTorch框架实现UNet网络，并展示了详细的网络结构代码。此外，还提供了模型测试代码，用于验证网络的有效性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

在AI Studio平台上有完整的工程文件，这里只展示Unet网络框架结构和pytorch框架实现的代码。在 PaddleSeg 套件中添加新的分割模型——Unet网络
Unet网络结构
代码由pytorch框架进行实现，上面链接的工程由paddlepaddle框架实现，可以对照查看。

import torch
from torch import nn
from torchkeras import summary

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

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


class Unet(nn.Module):
    def __init__(self,in_ch,out_ch):
        super(Unet, self).__init__()

        self.conv1 = DoubleConv(in_ch, 64)
        self.pool1 = nn.MaxPool2d(2)
        self.conv2 = DoubleConv(64, 128)
        self.pool2 = nn.MaxPool2d(2)
        self.conv3 = DoubleConv(128, 256)
        self.pool3 = nn.MaxPool2d(2)
        self.conv4 = DoubleConv(256, 512)
        self.pool4 = nn.MaxPool2d(2)
        self.conv5 = DoubleConv(512, 1024)
        self.up6 = nn.ConvTranspose2d(1024, 512, 2, stride=2)
        self.conv6 = DoubleConv(1024, 512)
        self.up7 = nn.ConvTranspose2d(512, 256, 2, stride=2)
        self.conv7 = DoubleConv(512, 256)
        self.up8 = nn.ConvTranspose2d(256, 128, 2, stride=2)
        self.conv8 = DoubleConv(256, 128)
        self.up9 = nn.ConvTranspose2d(128, 64, 2, stride=2)
        self.conv9 = DoubleConv(128, 64)
        self.conv10 = nn.Conv2d(64, out_ch, 1)

    def forward(self, x):
        c1 = self.conv1(x)
        p1 = self.pool1(c1)
        c2 = self.conv2(p1)
        p2 = self.pool2(c2)
        c3 = self.conv3(p2)
        p3 = self.pool3(c3)
        c4 = self.conv4(p3)
        p4 = self.pool4(c4)
        c5 = self.conv5(p4)
        up_6 = self.up6(c5)
        merge6 = torch.cat([up_6, c4], dim=1)
        c6=self.conv6(merge6)
        up_7 = self.up7(c6)
        merge7 = torch.cat([up_7, c3], dim=1)
        c7 = self.conv7(merge7)
        up_8 = self.up8(c7)
        merge8 = torch.cat([up_8, c2], dim=1)
        c8 = self.conv8(merge8)
        up_9 = self.up9(c8)
        merge9 = torch.cat([up_9, c1], dim=1)
        c9 = self.conv9(merge9)
        c10 = self.conv10(c9)
        return c10

model=Unet(3,3)
x = torch.randn((10, 3, 32, 32))
print(x)
# 测试模型前向计算
y = model(x)
print(y)
# 打印输出维度
print(y.shape)
summary(model,(3, 32, 32))