Tensorflow，为变量赋值

Question

我是 tensorflow 的新手，我正在学习

https://www.tensorflow.org/get_started/get_started

fixW = tf.assign(W, [-1.])

工作正常，但

fixb = tf.assign(b, [1.])
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/milenko/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 272, in assign
    return ref.assign(value)
AttributeError: 'Tensor' object has no attribute 'assign'

另一个例子

zero_tsr = tf.zeros([1.,2.])
zero_tsr
<tf.Tensor 'zeros:0' shape=(1, 2) dtype=float32>

如果我尝试更改 zero_tsr

fixz = tf.assign(zero_tsr, [2.,2.])
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/milenko/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 272, in assign
    return ref.assign(value)
AttributeError: 'Tensor' object has no attribute 'assign'

同样的问题。

我没有换过shell，一切都一样。为什么我这里有问题？

Answer 1

在您发布的示例中:

zero_tsr = tf.zeros([1.,2.])
zero_tsr
<tf.Tensor 'zeros:0' shape=(1, 2) dtype=float32>

zero_tsr是一个常数而不是一个变量，所以你不能给它赋值。

来自 the documentation :

assign( ref, value, validate_shape=None, use_locking=None, name=None )

ref: A mutable Tensor. Should be from a Variable node. May be uninitialized.

例如，这将正常工作:

import tensorflow as tf
zero_tsr = tf.Variable([0,0])
tf.assign(zero_tsr,[4,5])

虽然此代码会引发错误

import tensorflow as tf
zero_tsr = tf.zeros([1,2])
tf.assign(zero_tsr,[4,5])

引发的错误正是您发布的错误:

AttributeError: 'Tensor' object has no attribute 'assign'