slim.arg_scope中python技巧

slim.arg_scope函数说明如下：

Stores the default arguments for the given set of list_ops.
For usage, please see examples at top of the file.
Args:
list_ops_or_scope: List or tuple of operations to set argument scope for or
a dictionary containing the current scope. When list_ops_or_scope is a
dict, kwargs must be empty. When list_ops_or_scope is a list or tuple,
then every op in it need to be decorated with @add_arg_scope to work.
**kwargs: keyword=value that will define the defaults for each op in
list_ops. All the ops need to accept the given set of arguments.
Yields:
the current_scope, which is a dictionary of {op: {arg: value}}
Raises:
TypeError: if list_ops is not a list or a tuple.
ValueError: if any op in list_ops has not be decorated with @add_arg_scope.

因此使用@slim.add_arg_scope修饰目标函数，从而达到用slim.arg_scope为目标函数设置默认参数的目的。而库中的conv2d等函数，已经被默认声明。因此，可以在构建网络时，快捷设置，达到节省时间的目的。同时，也可以通过下面的方式进行单独设置。

with slim.arg_scope(
    [slim.conv2d,slim.max_pool2d],stride = 1,padding = 'SAME'):
    net = slim.conv2d(net,32,[3,3],stride=2,scope = 'conv1')

装饰器@

# 装饰器
import time
 
# 装饰器,记录函数运行时间
def decorator01(fun):
    def wapper():
        stime = time.time()#'装饰'
        fun()#第三步：执行函数功能
        etime = time.time()#’装饰‘
        print("fun run time is {TIME}".format(TIME=etime - stime))
    return wapper  # 必须要返回一个函数的内存地址
 
#第一步运行到这里的时候， 使用装饰器装饰某个函数,这里等价于 test01=decorator01(test01),（所谓装饰之意？）
# 即将test01实际引用变成wapper函数内存地址,所以执行test01实际是执行wapper
@decorator01
def test01():
    time.sleep(2)
    print("test01 is running")
 
 #第二步：这里的时候就执行wapper()了，
test01()  # 不修改代码和调用方式,实现添加记录时间功能

slim.arg_scope中python技巧

原文：https://www.cnblogs.com/zy-blogs/p/10458561.html