tf.Variable和tf.get_variable的区别

关于变量的字段区别和使用

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

区别

本质区别：

       tf.Variable在同一变量空间中，创建名字相同的变量时，系统会解决命名冲突；tf.get_variable在同一变量空间中，如果变量命名相同时，将共享变量，不会再创建新的变量。

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?

共享变量：    

 基于这两个函数的特性，当我们在同一变量空间中可以用来共享变量，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

使用区别：

tf.Variable使用方法

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.Variable(initial_value,name,dtype) 

常用的属性：initial_value, name, dtype。即需要指定值（，名字，数值类型）

import tensorflow as tf
v1=tf.Variable(tf.random_normal(shape=[4,3],mean=0,stddev=1),name='v1')
v2=tf.Variable(tf.constant(2),name='v2')
v3=tf.Variable(tf.ones([4,3]),name='v3')
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(v1))
    print(sess.run(v2))
    print(sess.run(v3))

常用于初始化的tensor，如下

random tensor

tf.random_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)

tf.truncated_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)

tf.random_uniform(shape, minval=0, maxval=None, dtype=tf.float32, seed=None, name=None)

tf.random_shuffle(value, seed=None, name=None)

tf.random_crop(value, size, seed=None, name=None)

tf.multinomial(logits, num_samples, seed=None, name=None)

tf.random_gamma(shape, alpha, beta=None, dtype=tf.float32, seed=None, name=None)

tf.set_random_seed(seed)

 constant tensor

tf.zeros(shape, dtype=tf.float32, name=None)

tf.zeros_like(tensor, dtype=None, name=None)

tf.ones(shape, dtype=tf.float32, name=None)

tf.ones_like(tensor, dtype=None, name=None)

tf.fill(dims, value, name=None)

tf.constant(value, dtype=None, shape=None, name='Const')

tf.get_variable使用方法

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)

常用的属性，name,shape和initializer ，需要指定类型和初始化的方式，而不是将值直接赋予

tf.get_variable(name, shape, initializer): name就是变量的名称，shape是变量的维度，initializer是变量初始化的方式

import tensorflow as tf;  
  
a1 = tf.get_variable(name='a1', shape=[2,3], initializer=tf.random_normal_initializer(mean=0, stddev=1))
a2 = tf.get_variable(name='a2', shape=[1], initializer=tf.constant_initializer(1))
a3 = tf.get_variable(name='a3', shape=[2,3], initializer=tf.ones_initializer())
 
with tf.Session() as sess:
    sess.run(tf.initialize_all_variables())
    print sess.run(a1)
    print sess.run(a2)

initializer

tf.constant_initializer(value=0, dtype=tf.float32)
tf.random_normal_initializer(mean=0.0, stddev=1.0, seed=None, dtype=tf.float32)
tf.truncated_normal_initializer(mean=0.0, stddev=1.0, seed=None, dtype=tf.float32)
tf.random_uniform_initializer(minval=0, maxval=None, seed=None, dtype=tf.float32)
tf.uniform_unit_scaling_initializer(factor=1.0, seed=None, dtype=tf.float32)
tf.zeros_initializer(shape, dtype=tf.float32, partition_info=None)
tf.ones_initializer(dtype=tf.float32, partition_info=None)
tf.orthogonal_initializer(gain=1.0, dtype=tf.float32, seed=None)

参考资料

https://blog.csdn.net/js54100804/article/details/80463520

https://www.jianshu.com/p/d80a21489184

https://www.w3cschool.cn/tensorflow_python/tensorflow_python-st6f2ez1.html

https://blog.csdn.net/yunyi4367/article/details/80482213

https://blog.csdn.net/qq_37913997/article/details/80352191

https://blog.csdn.net/MrR1ght/article/details/81228087