如何为TensorFlow变量分配值? [英] How to assign a value to a TensorFlow variable?

问题描述

我正在尝试为python中的tensorflow变量分配一个新值.

I am trying to assign a new value to a tensorflow variable in python.

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())

但是我得到的输出是

0
0

因此该值未更改.我想念什么?

So the value has not changed. What am I missing?

推荐答案

在TF1中，语句 Operation.run() 或

In TF1, the statement x.assign(1) does not actually assign the value 1 to x, but rather creates a tf.Operation that you have to explicitly run to update the variable.* A call to Operation.run() or Session.run() can be used to run the operation:

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

(*实际上，它返回与变量的更新值相对应的tf.Tensor，以便更轻松地进行链式分配.)

(* In fact, it returns a tf.Tensor, corresponding to the updated value of the variable, to make it easier to chain assignments.)

但是，在TF2中， x.assign(1) 现在将分配渴望价值:

However, in TF2 x.assign(1) will now assign the value eagerly:

x.assign(1)
print(x.numpy())
# ==> 1

这篇关于如何为TensorFlow变量分配值?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！