开局一张图，首先抛出vgg11的网络架构（完整版放在文章最下方）
下面，再配合pytorch官方代码，解析一下vgg11。以vgg11为切入点，由浅入深，理解vgg架构
源码解析demo
import torchvision.models as modelsvgg11 = models.vgg11(pretrained=True)print(vgg11)
ctrl+鼠标左键点击vgg11，进入vgg.py文件下 映入眼帘的是vgg11的构造函数
vgg11分为两种：
不带BN层（‘A’后面的参数为False）
def vgg11(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG: r"""VGG 11-layer model (configuration "A") from `"Very Deep Convolutional Networks For Large-Scale Image Recognition"
带BN层（‘A’后面的参数为True）
def vgg11_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG: r"""VGG 11-layer model (configuration "A") with batch normalization `"Very Deep Convolutional Networks For Large-Scale Image Recognition"
构造函数用到了_vgg()方法来创建网络
def _vgg(arch: str, cfg: str, batch_norm: bool, pretrained: bool, progress: bool, **kwargs: Any) -> VGG: if pretrained:#如果加载预训练模型，那么就不初始化权重 kwargs['init_weights'] = False model = VGG(make_layers(cfgs[cfg], batch_norm=batch_norm), **kwargs) if pretrained: state_dict = load_state_dict_from_url(model_urls[arch], progress=progress) model.load_state_dict(state_dict) return model
再看VGG方法的第一个参数make_layers(cfgs[cfg], batch_norm=batch_norm)
ctrl+鼠标左键点击cfgs，跳转到cfgs
cfgs: Dict[str, List[Union[str, int]]] = { #根据网络结构和参数设置，构造 cfgs 字典，存放这些结构参数 'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],#数字代表卷积层输出特征图通道数，M 代表最大池化层 'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'], 'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'], 'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],}
然后返回上一级，ctrl+鼠标左键点击make_layers
这函数负责构建特征提取网络
def make_layers(cfg: List[Union[str, int]], batch_norm: bool = False) -> nn.Sequential: layers: List[nn.Module] = [] # 层列表初始化 in_channels = 3 #RGB图像为3通道 for v in cfg: if v == 'M': # 添加池化层 核大小和步长都为2 layers += [nn.MaxPool2d(kernel_size=2, stride=2)] else:#添加卷积层 v = cast(int, v)#检查v的type conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1) # 3×3 卷积 if batch_norm: layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)] else: layers += [conv2d, nn.ReLU(inplace=True)] in_channels = v#下一层的channel是上一层的out_channel return nn.Sequential(*layers)
接下来，返回上一级
在_vgg()方法中，又调用了VGG()方法创建模型
class VGG(nn.Module): def __init__( self, features: nn.Module, num_classes: int = 1000, init_weights: bool = True ) -> None: super(VGG, self).__init__() self.features = features #特征提取部分 self.avgpool = nn.AdaptiveAvgPool2d((7, 7))## 自适应平均池化，特征图池化到 7×7 大小 # 分类部分 self.classifier = nn.Sequential( nn.Linear(512 * 7 * 7, 4096), nn.ReLU(True), nn.Dropout(), nn.Linear(4096, 4096), nn.ReLU(True), nn.Dropout(), nn.Linear(4096, num_classes), ) if init_weights:# 权重初始化 self._initialize_weights() def forward(self, x: torch.Tensor) -> torch.Tensor: # 特征提取 x = self.features(x) # 自适应平均池化 x = self.avgpool(x) # 展平 x = torch.flatten(x, 1) # 分类 x = self.classifier(x) return x ``` pytorch官方实现做了一点改进，用的自适应平均池化，为的让下一步flatten操作接收固定向量，网络能够喂入不同大小的输入 分类这块，pytorch官方加入了两个dropout操作 ``` def _initialize_weights(self) -> None: for m in self.modules(): if isinstance(m, nn.Conv2d):# 卷积层使用 kaimming 初始化 nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') if m.bias is not None:# 偏置初始化为0 nn.init.constant_(m.bias, 0) elif isinstance(m, nn.BatchNorm2d):# BN层权重初始化为1 nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) elif isinstance(m, nn.Linear):#全连接层权重初始化 nn.init.normal_(m.weight, 0, 0.01) nn.init.constant_(m.bias, 0)
解析完毕，总体来说vgg采用堆叠小卷积核来实现与大卷积核一样的感受野，而增大网络的深度，引入了多个非线性，增强了网络的拟合能力。从参数量来看，多个堆叠小卷积核减少了参数量。从卷积核大小来看，堆叠多个小卷积核来代替大卷积核，相当于对大卷积核引入正则化，增强了网络的健壮性特征提取。
最后，再对照vgg11完整网络结构，理解一下vgg架构。