Tensorflow教程(十三) tf.Variable() 和tf.get_variable()

1 简介

tf.Variable()

tf.Variable(initial_value=None, trainable=True, collections=None, validate_shape=True, 
caching_device=None, name=None, variable_def=None, dtype=None, expected_shape=None, 
import_scope=None)

tf.get_variable()

tf.get_variable(name, shape=None, dtype=None, initializer=None, regularizer=None, 
trainable=True, collections=None, caching_device=None, partitioner=None, validate_shape=True, 
custom_getter=None)

2 区别

1、使用tf.Variable时，如果检测到命名冲突，系统会自己处理。使用tf.get_variable()时，系统不会处理冲突，而会报错

import tensorflow as tf
w_1 = tf.Variable(3,name="w_1")
w_2 = tf.Variable(1,name="w_1")
print w_1.name
print w_2.name
#输出
#w_1:0
#w_1_1:0

import tensorflow as tf

w_1 = tf.get_variable(name="w_1",initializer=1)
w_2 = tf.get_variable(name="w_1",initializer=2)
#错误信息
#ValueError: Variable w_1 already exists, disallowed. Did
#you mean to set reuse=True in VarScope?

2、基于这两个函数的特性，当我们需要共享变量的时候，需要使用tf.get_variable()。在其他情况下，这两个的用法是一样的

import tensorflow as tf

with tf.variable_scope("scope1"):
    w1 = tf.get_variable("w1", shape=[])
    w2 = tf.Variable(0.0, name="w2")
with tf.variable_scope("scope1", reuse=True):
    w1_p = tf.get_variable("w1", shape=[])
    w2_p = tf.Variable(1.0, name="w2")

print(w1 is w1_p, w2 is w2_p)
#输出
#True  False

由于tf.Variable() 每次都在创建新对象，所有reuse=True 和它并没有什么关系。对于get_variable()，来说，如果已经创建的变量对象，就把那个对象返回，如果没有创建变量对象的话，就创建一个新的。

以上内容来自于：tensorflow学习笔记（二十三）：variable与get_variable

3 实例

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

import tensorflow as tf

x1 = tf.truncated_normal([200, 100], name='x1')
x2 = tf.truncated_normal([200, 100], name='x2')

def two_hidden_layers_1(x):
    assert x.shape.as_list() == [200, 100]
    w1 = tf.Variable(tf.random_normal([100, 50]), name='h1_weights')
    b1 = tf.Variable(tf.zeros([50]), name='h1_biases')
    h1 = tf.matmul(x, w1) + b1
    assert h1.shape.as_list() == [200, 50]
    w2 = tf.Variable(tf.random_normal([50, 10]), name='h2_weights')
    b2 = tf.Variable(tf.zeros([10]), name='2_biases')
    logits = tf.matmul(h1, w2) + b2
    return logits

def two_hidden_layers_2(x):
    assert x.shape.as_list() == [200, 100]
    w1 = tf.get_variable('h1_weights', [100, 50], initializer=tf.random_normal_initializer())
    b1 = tf.get_variable('h1_biases', [50], initializer=tf.constant_initializer(0.0))
    h1 = tf.matmul(x, w1) + b1
    assert h1.shape.as_list() == [200, 50]
    w2 = tf.get_variable('h2_weights', [50, 10], initializer=tf.random_normal_initializer())
    b2 = tf.get_variable('h2_biases', [10], initializer=tf.constant_initializer(0.0))
    logits = tf.matmul(h1, w2) + b2
    return logits


def fully_connected(x, output_dim, scope):
    with tf.variable_scope(scope, reuse=tf.AUTO_REUSE) as scope:
        w = tf.get_variable('weights', [x.shape[1], output_dim], initializer=tf.random_normal_initializer())
        b = tf.get_variable('biases', [output_dim], initializer=tf.constant_initializer(0.0))
        return tf.matmul(x, w) + b

def two_hidden_layers_3(x):
    h1 = fully_connected(x, 50, 'h1')
    h2 = fully_connected(h1, 10, 'h2')
    return h2
# with tf.variable_scope('two_layers') as scope:
#     logits1 = two_hidden_layers_1(x1) 
#     # scope.reuse_variables()
#     logits2 = two_hidden_layers_1(x2)
# 不会报错
# ---------------

# with tf.variable_scope('two_layers') as scope:
#     logits1 = two_hidden_layers_2(x1)
#     # scope.reuse_variables()
#     logits2 = two_hidden_layers_2(x2)
# 会报错
# ---------------

with tf.variable_scope('two_layers') as scope:
    logits1 = two_hidden_layers_3(x1)
    # scope.reuse_variables()
    logits2 = two_hidden_layers_3(x2)
# 不会报错
# -------
writer = tf.summary.FileWriter('./graphs/cool_variables', tf.get_default_graph())
writer.close()