Tensorflow：如何分配變量正確

Question

這不是重複的How to assign value to a tensorflow variable?

我試圖做simpliest件事：只是交換變量Tensorflow: how to swap variables between scopes and set variables in scope from another， 我還是不能做到這一點。

但是現在我知道assign更改張量的副本，我用tf.identity得到張量。我不想要這個。我需要交換變量的副本。

In [10]: a = tf.Variable(1) 

In [11]: b = tf.identity(a) 

In [12]: a += 1 

In [14]: sess.run(a) 
Out[14]: 2 

In [15]: sess.run(b) 
Out[15]: 1 

In [16]: a = tf.Variable(1) 

In [17]: b = tf.identity(a) 

In [18]: assign_t = a.assign(2) 

In [20]: sess.run(tf.initialize_all_variables()) 

In [21]: sess.run(a) 
Out[21]: 1 

In [22]: sess.run(assign_t) 
Out[22]: 2 

In [23]: sess.run(a) 
Out[23]: 2 

In [24]: sess.run(b) 
Out[24]: 2 

我怎麼能值分配給a不改變b？

Answer 1

tf.identity()操作是無狀態的。當你有一個叫做a的tf.Variable時，tf.identity(a)的值將始終與a的值相同。如果你想b記住的a以前的值，你應該創建b爲tf.Variable還有：

a = tf.Variable(1) 
b = tf.Variable(a.initialized_value()) 

sess.run(tf.global_variables_initializer()) 

# Initially, variables `a` and `b` have the same value. 
print(sess.run([a, b])) ==> [1, 1] 

# Update the value of `a` to 2. 
assign_op = a.assign(2) 
sess.run(assign_op) 

# Now, `a` and `b` have different values. 
print(sess.run([a, b])) ==> [2, 1]