PyTorch 目标检测（六）

SSD 网络框架

SSD在VGGNet的基础上又增加了多个卷积层，并利用多个特征图进行边框提取得到深层网络，之后利用人为设置的PriorBox与标签内的边框进行匹配，根据重叠程度筛选出正负样本，得到分类与偏移的真值然后与预测值一同计算损失.

SSD的VGG16

输入经过SSD预处理后大小固定为300300，之后进入VGG16基础网络，SSD保留了VGG的前13层卷积网络，之后添加了Conv6和Conv7取代了全连接网络。Conv6中使用了空洞数为6的空洞卷积，并且padding也为6，这样可以在维持特征图尺寸不变时增加感受野。Conv7为11的卷积层降低了维数以便减少参数数量。此外VGG的池化层参数也有所改变。

ssd.py中VGG16的定义

def vgg(cfg, i, batch_norm=False):
    layers = []
    in_channels = i
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        elif v == 'C':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)]
        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
    pool5 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
    conv6 = nn.Conv2d(512, 1024, kernel_size=3, padding=6, dilation=6)
    conv7 = nn.Conv2d(1024, 1024, kernel_size=1)
    layers += [pool5, conv6,
               nn.ReLU(inplace=True), conv7, nn.ReLU(inplace=True)]
    return layers
    
base = {
    '300': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M',
            512, 512, 512],
    '512': [],
}
ssd_vgg = vgg(base['300'],3) 完成基础网络构造

深度卷积层

SSD在VGG16（包括conv6,conv7）之后又添加了四个深度卷积层，

def add_extras(cfg, i, batch_norm=False):
   # Extra layers added to VGG for feature scaling
   layers = []
   in_channels = i
   flag = False
   for k, v in enumerate(cfg):
       if in_channels != 'S':
           if v == 'S':
               layers += [nn.Conv2d(in_channels, cfg[k + 1],
                          kernel_size=(1, 3)[flag], stride=2, padding=1)]
           else:
               layers += [nn.C