深度残差收缩网络的pytorch代码

以下是深度残差收缩网络的 PyTorch 代码：

import torch
import torch.nn as nn

class ResidualShrinkageBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, padding=1, dilation=1, 
                 reduction_ratio=16, last=False):
        super(ResidualShrinkageBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, 
                               padding=padding, dilation=dilation, 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=padding, dilation=dilation, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.last = last
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc1 = nn.Linear(out_channels, out_channels // reduction_ratio)
        self.fc2 = nn.Linear(out_channels // reduction_ratio, out_channels)
        self.sigmoid = nn.Sigmoid()

    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.last:
            out = out
        else:
            out = self.avg_pool(out)
            out = out.view(out.size(0), -1)
            out = self.fc1(out)
            out = self.relu(out)
            out = self.fc2(out)
            out = self.sigmoid(out)
            out = out.view(out.size(0), out.size(1), 1, 1)
            out = out * identity

        out += identity
        out = self.relu(out)

        return out

class ResidualShrinkageNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(ResidualShrinkageNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(64, 256, 3)
        self.layer2 = self._make_layer(256, 512, 4, stride=2)
        self.layer3 = self._make_layer(512, 1024, 6, stride=2)
        self.layer4 = self._make_layer(1024, 2048, 3, stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(2048, num_classes)

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

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

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

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x

这是一个四层残差结构的 Residual Shrinkage Net，其中每个残差块有一个特殊的缩减层，用于减少冗余特征。可以根据需要调整层数和通道数。