resnet34和resnet50结构图和区别

### ResNet34与ResNet50的网络结构及其差异

#### ResNet34架构特点
ResNet34属于较浅版本的残差网络，采用了基本的残差块设计。该模型由多个堆叠的基础模块组成，每个基础模块通常包含两个3×3的卷积层[^4]。

class BasicBlock(nn.Module):
    expansion = 1
    
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        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.downsample is not None:
            identity = self.downsample(x)

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

        return out

#### ResNet50架构特点
相比之下，ResNet50则运用了更复杂的瓶颈（Bottleneck）结构来替代简单的双层卷积单元。这种改进不仅提高了计算资源利用率，还增强了特征表达能力。具体来说，每一个Bottleneck block包含了三个不同尺寸的卷积操作——首先是压缩通道数至四分之一的一维卷积；其次是标准的空间感知三维卷积；最后再扩展回原始宽度的一维卷积[^2]。

class Bottleneck(nn.Module):
    expansion = 4
    
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = conv1x1(inplanes, planes)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = conv1x1(planes, planes * self.expansion)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        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)
        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

#### 主要区别总结
- **层数**：ResNet34总共拥有34个权重层，而ResNet50有50个。
- **block类型**：前者采用Basic Block作为构建单位，后者则是更为高效的Bottleneck Block。
- **参数量和计算成本**：由于使用了更多层次以及更加精细的设计，ResNet50虽然更深但是却能在一定程度上减少整体参数数目并提高运行效率。