OrderedDict构建函数模块的不常见写法

常见写法是直接把所有的子模块直接写在OrderedDict里面，即OrderedDict（[(‘A’, XXX), (‘B’, YYY)] ）不常见写法如下：

  head = OrderedDict()

 head.update({"project_conv": ConvBNAct(head_input_c,
                                               num_features,
                                               kernel_size=1,
                                               norm_layer=norm_layer)})  # 激活函数默认是SiLU

head.update({"avgpool": nn.AdaptiveAvgPool2d(1)})
head.update({"flatten": nn.Flatten()})

if dropout_rate > 0:
   head.update({"dropout": nn.Dropout(p=dropout_rate, inplace=True)})
   head.update({"classifier": nn.Linear(num_features, num_classes)})

   self.head = nn.Sequential(head)

注意事项：nn.Sequential传入head时不用像传递list类型对象那样需要加一个*的标号