pytorch框架UNet图像分割代码示例

以下是一个基于PyTorch框架实现的UNet图像分割代码示例：

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

class DoubleConv(nn.Module):
    """Double convolution layer with batch normalization and ReLU activation"""
    def __init__(self, in_channels, out_channels):
        super(DoubleConv, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

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

class UNet(nn.Module):
    """UNet architecture for image segmentation"""
    def __init__(self, in_channels=3, out_channels=1, features=[64, 128, 256, 512]):
        super(UNet, self).__init__()
        self.downs = nn.ModuleList()
        self.ups = nn.ModuleList()
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)

        # Encoder
        for feature in features:
            self.downs.append(DoubleConv(in_channels, feature))
            in_channels = feature

        # Decoder
        for feature in reversed(features):
            self.ups.append(nn.ConvTranspose2d(feature*2, feature, kernel_size=2, stride=2))
            self.ups.append(DoubleConv(feature*2, feature))

        self.bottleneck = DoubleConv(features[-1], features[-1]*2)
        self.final_conv = nn.Conv2d(features[0], out_channels, kernel_size=1)

    def forward(self, x):
        skip_connections = []

        # Encoder
        for down in self.downs:
            x = down(x)
            skip_connections.append(x)
            x = self.pool(x)

        # Bottleneck
        x = self.bottleneck(x)

        # Decoder
        skip_connections = skip_connections[::-1]
        for idx in range(0, len(self.ups), 2):
            x = self.ups[idx](x)
            skip_connection = skip_connections[idx//2]
            if x.shape != skip_connection.shape:
                x = F.interpolate(x, size=skip_connection.shape[2:], mode='bilinear', align_corners=True)
            x = torch.cat((skip_connection, x), dim=1)
            x = self.ups[idx+1](x)

        # Final convolution
        x = self.final_conv(x)
        return x

这个代码实现了一个UNet模型，包括Encoder和Decoder部分，以及一个bottleneck层和一个最终的卷积层。UNet模型的核心思想是在Encoder部分通过不断下采样（使用MaxPooling）来提取图像的低级特征，然后在Decoder部分通过上采样（使用ConvTranspose2d）和跳过连接（skip connections）来逐渐恢复图像的分辨率并提取高级特征，最终输出图像的分割结果。在这个实现中，我们使用了双卷积层（DoubleConv）作为UNet的基本构建块，每个双卷积层都包含两个卷积层、批量归一化和ReLU激活函数。UNet的输入是一个3通道的图像，输出是一个1通道的分割结果。可以根据具体的应用场景，调整输入和输出的通道数，以及Encoder和Decoder的层数和特征数。