写一个resnet50

以下是ResNet50的PyTorch实现，包含了残差块（Residual Block）和网络结构的定义：

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

class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.conv3 = nn.Conv2d(out_channels, out_channels * 4, kernel_size=1, stride=1, bias=False)
        self.bn3 = nn.BatchNorm2d(out_channels * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample

    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)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            identity = self.downsample(x)

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

        return out

class ResNet50(nn.Module):
    def __init__(self, num_classes=1000):
        super(ResNet50, self).__init__()
        self.in_channels = 64
        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(ResidualBlock, 64, 3)
        self.layer2 = self._make_layer(ResidualBlock, 128, 4, stride=2)
        self.layer3 = self._make_layer(ResidualBlock, 256, 6, stride=2)
        self.layer4 = self._make_layer(ResidualBlock, 512, 3, stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * 4, num_classes)

    def _make_layer(self, block, out_channels, num_blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels * 4):
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channels, out_channels * 4, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels * 4),
            )

        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels * 4
        for i in range(1, num_blocks):
            layers.append(block(self.in_channels, out_channels))

        return nn.Sequential(*layers)

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

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

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

        return out

ResNet50包含了4个残差块（layer1，layer2，layer3，layer4），每个残差块包含多个残差块（Residual Block）。Residual Block由3个卷积层组成，其中第1、2层是3x3的卷积，第3层是1x1的卷积。在每个残差块的第1个Residual Block中，会使用downsample将输入x的大小调整到与输出一致，以便进行加法运算。最后通过全局平均池化和全连接层得到输出。