如何为TensorFlow变量赋值？

我试图在python中为tensorflow变量赋一个新值.

import tensorflow as tf
import numpy as np

x = tf.Variable(0)
init = tf.initialize_all_variables()
sess = tf.InteractiveSession()
sess.run(init)

print(x.eval())

x.assign(1)
print(x.eval())

但我得到的输出是

0
0

所以价值没有改变.我错过了什么？

该声明x.assign(1)实际上并没有赋值1给x,而是创建了一个tf.Operation,你必须明确地运行更新变量*要在通话.Operation.run()或Session.run()可用于运行操作:

assign_op = x.assign(1)
sess.run(assign_op)  # or `assign_op.op.run()`
print(x.eval())
# ==> 1

(*实际上,它返回一个tf.Tensor,对应于变量的更新值,以便更容易链接赋值.)

您也可以在tf.Variable不向图表添加操作的情况下为a分配新值:tf.Variable.load(value, session).此函数还可以在从图形外部指定值时保存添加占位符,并且在图形完成时非常有用.

import tensorflow as tf
x = tf.Variable(0)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
print(sess.run(x))  # Prints 0.
x.load(1, sess)
print(sess.run(x))  # Prints 1.

import tensorflow as tf
x = tf.Variable(0)
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print sess.run(x, feed_dict={x: 3})

import tensorflow as tf
x = tf.Variable(0)
y = tf.assign(x, 1)
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print sess.run(x)
    print sess.run(y)
    print sess.run(x)