残差网络 python

下面是一个简单的残差网络的 Python 实现示例：

import torch
import torch.nn as nn

class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.stride != 1 or identity.size(1) != out.size(1):
            identity = nn.Conv2d(identity.size(1), out.size(1), kernel_size=1, stride=self.stride, bias=False)(identity)
            identity = nn.BatchNorm2d(out.size(1))(identity)
        
        out += identity
        out = self.relu(out)

        return out


class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 64

        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)

        self.layer1 = self.make_layer(block, 64, layers[0], stride=1)
        self.layer2 = self.make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self.make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self.make_layer(block, 512, layers[3], stride=2)

        self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, out_channels, blocks, stride=1):
        layers = []
        layers.append(block(self.in_channels, out_channels, stride))
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(block(self.in_channels, out_channels, stride=1))
        return nn.Sequential(*layers)

    def forward(self, x):
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)

        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)

        return out

该示例中定义了一个 ResidualBlock 类和一个 ResNet 类，用于构建残差网络的基本组件。其中，ResidualBlock 类和前面提到的残差块的实现非常相似，用于构建残差网络的基本单元；ResNet 类则是整个残差网络的实现，它使用了多个 ResidualBlock 组成的层来构建网络。

在 ResNet 类的初始化函数中，首先定义了一个卷积层、一个批归一化层和一个 ReLU 激活函数，用于对输入图像进行预处理。然后，通过 make_layer 方法和多个 ResidualBlock 组成的层来构建整个网络。最后，使用一个全局平均池化层和一个全连接层输出分类结果。在 make_layer 方法中，使用了多个 ResidualBlock 组成的层，其中第一个 ResidualBlock 的 stride 参数可能不为 1，用于进行降采样。

该示例中的残差网络是一个用于 CIFAR-10 数据集的简单实现，可以根据实际需要进行修改。