是否允许在变量进入计算图之前为其赋值? [英] Is it allowed to assign a value to a variable before it enter a computational graph?

问题描述

我定义了一个涉及变量的简单计算图.当我更改变量的值时，它会对计算图的输出产生预期的影响(因此，一切正常，正如预期的那样):

I define a simple computational graph involving a variable. When I change a value of the variable it has an expected influence on the output of the computational graph (so, everything works fine, as expected):

s = tf.Session()

x = tf.placeholder(tf.float32)
c = tf.Variable([1.0, 1.0, 1.0], tf.float32)

y = x + c

c = tf.assign(c, [3.0, 3.0, 3.0])   
s.run(c)
print 'Y1:', s.run(y, {x : [10.0, 20.0, 30.0]})

c = tf.assign(c, [2.0, 2.0, 2.0])
s.run(c)
print 'Y2:',  s.run(y, {x : [10.0, 20.0, 30.0]})

当我调用此代码时，我得到:

When I call this code I get:

Y1: [ 13.  23.  33.]
Y2: [ 12.  22.  32.]

所以，Y1 和 Y2 后面的值是不同的，正如预期的那样，因为它们是用不同的 c 值计算的.

So, the values after the Y1 and Y2 are different, as expected, because they are calculated with different values of c.

如果我在定义变量 c 的计算方式之前为其赋值，问题就开始了.在这种情况下，我无法分配 c 的新值.

The problems start if I assign a value to the variable c before I define how it is involved into calculation of y. In this case I cannot assign a new value of c.

s = tf.Session()

x = tf.placeholder(tf.float32)
c = tf.Variable([1.0, 1.0, 1.0], tf.float32)

c = tf.assign(c, [4.0, 4.0, 4.0])   # this is the line that causes problems
y = x + c

c = tf.assign(c, [3.0, 3.0, 3.0])   
s.run(c)
print 'Y1:', s.run(y, {x : [10.0, 20.0, 30.0]})

c = tf.assign(c, [2.0, 2.0, 2.0])
s.run(c)
print 'Y2:',  s.run(y, {x : [10.0, 20.0, 30.0]})

作为我得到的输出:

Y1: [ 14.  24.  34.]
Y2: [ 14.  24.  34.]

如您所见，每次计算 y 时，我都会得到涉及 c 旧值的结果.这是为什么?

As you can see, each time I calculate y, I get results involving the old values of c. Why is that?

推荐答案

使用 TensorFlow，请始终牢记您正在构建一个 计算图.在您的第一个代码片段中，您基本上定义了 y = tf.placeholder(tf.float32) + tf.Variable([1.0, 1.0, 1.0], tf.float32).在第二个示例中，您定义 y = tf.placeholder(tf.float32) + tf.assign(tf.Variable([1.0, 1.0, 1.0], tf.float32), [4.0, 4.0, 4.0]).

With TensorFlow, always keep in mind that you're building a computation graph. In your first code snippet, you basically define y = tf.placeholder(tf.float32) + tf.Variable([1.0, 1.0, 1.0], tf.float32). In your second example, you define y = tf.placeholder(tf.float32) + tf.assign(tf.Variable([1.0, 1.0, 1.0], tf.float32), [4.0, 4.0, 4.0]).

因此，无论您分配给 c 哪个值，计算图都包含 assign 操作，并将始终分配 [4.0, 4.0, 4.0] 在计算总和之前添加它.

So, no matter which value you assign to c, the computation graph contains the assign operation and will always assign [4.0, 4.0, 4.0] to it before computing the sum.

这篇关于是否允许在变量进入计算图之前为其赋值?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！