pytorch Vgg源码阅读

要实现VGG16，主要需要两个类
VGG和VGG16

我们通过VGG16调用VGG

这两个类的实现在VGG.PY中实现

首先我们来看看VGG类的实现

class VGG(nn.Module):

    def __init__(self, features, num_classes=1000, init_weights=True):
        super(VGG, self).__init__()
        self.features = features
        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:
            self._initialize_weights()

self.features代表了特征提取层的结构
有以下结构可以选择,也就是 self.features可以是以下ABCDE中的一种，表示成不同深度的VGG按网络

cfg = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    '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'],
}

self.classifier 表明了之后的全连接层的结构，也就是用来分类的分类器结构

我们以调用VGG16为例子，看看 self.features是如何构建的，

def vgg16(pretrained=False, **kwargs):
   """VGG 16-layer model (configuration "D")

   Args:
       pretrained (bool): If True, returns a model pre-trained on ImageNet
   """
   if pretrained:
       kwargs['init_weights'] = False
   model = VGG(make_layers(cfg['D']), **kwargs)
   if pretrained:
       model.load_state_dict(model_zoo.load_url(model_urls['vgg16']))
   return model

我们来看看步骤：

model = VGG(make_layers(cfg['D']), **kwargs)

1.调用cfg[‘D’]，我们来看看D表示什么

'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],

显然他定义了多个卷积层的结构，我们来看看
make_layers（cfg[‘D’]）做了什么，

def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)

显然现在我们的self.features = features 变成了一系列卷积层和pooling层
ABDE表明乐不同的VGG网络结构