Tensorflow Slim用法

TF-Slim 是Tensorflow为了定义、训练和评估复杂模型的一个轻量级工具

用户通过样板代码使模型的定义更加紧凑，提高了可读性和可维护性，通过复制粘贴超参数值降低了人工输入出错的可能性，并简化了超参数调优。

TF-Slim的导入
import tensorflow.contrib.slim as slim

Tensorflow Slim中slim.arg_scope的用法

arg_scope(list_ops_or_scope,kwargs)

list_ops_or_scope: 操作列表或操作域
kwargs: 设置的参数，以keyword=value方式显示

未用slim简化前：
net = slim.conv2d(inputs, 64, [11, 11], 4, padding='SAME', weights_initializer=tf.truncated_normal_initializer(stddev=0.01), weights_regularizer=slim.l2_regularizer(0.0005), scope='conv1')

net = slim.conv2d(net, 128, [11, 11], padding='VALID', weights_initializer=tf.truncated_normal_initializer(stddev=0.01), weights_regularizer=slim.l2_regularizer(0.0005), scope='conv2')

net = slim.conv2d(net, 256, [11, 11], padding='SAME', weights_initializer=tf.truncated_normal_initializer(stddev=0.01), weights_regularizer=slim.l2_regularizer(0.0005), scope='conv3')

slim简化后：
with slim.arg_scope([slim.conv2d], padding='SAME', weights_initializer=tf.truncated_normal_initializer(stddev=0.01) weights_regularizer=slim.l2_regularizer(0.0005)): //参数模板

net = slim.conv2d(inputs, 64, [11, 11], scope='conv1')
net = slim.conv2d(net, 128, [11, 11], padding='VALID', scope='conv2')
net = slim.conv2d(net, 256, [11, 11], scope='conv3')