使用tf.gradients时的Tensorflow错误：TypeError：Fetch参数None具有无效类型<type 'NoneType'>

Question

我刚开始学习tensorflow并在使用tf.gradients函数时遇到以下错误。 下面给出了tf.gradients的代码和错误。

Python代码：

import tensorflow as tf

if __name__ =='__main__':

    os.environ['CUDA_VISIBLE_DEVICES'] = "0"

    w1 = tf.Variable([[1, 2]])
    w2 = tf.Variable([[2], [1]])

    res = tf.matmul(w1,w2)

    grads = tf.gradients(res, [w1,w2])

    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        print(sess.run(res))
        re = sess.run(grads)
        print(re)

错误：

[[4]]
    re = sess.run(grads)
  File "/home/BH/fyn123456/.conda/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run
    run_metadata_ptr)
  File "/home/BH/fyn123456/.conda/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1137, in _run
    self._graph, fetches, feed_dict_tensor, feed_handles=feed_handles)
  File "/home/BH/fyn123456/.conda/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 471, in __init__
    self._fetch_mapper = _FetchMapper.for_fetch(fetches)
  File "/home/BH/fyn123456/.conda/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 261, in for_fetch
    return _ListFetchMapper(fetch)
  File "/home/BH/fyn123456/.conda/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 370, in __init__
    self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches]
  File "/home/BH/fyn123456/.conda/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 370, in <listcomp>
    self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches]
  File "/home/BH/fyn123456/.conda/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 258, in for_fetch
    type(fetch)))
TypeError: Fetch argument None has invalid type <class 'NoneType'>

Answer 1

我的变量是整数类型（因为你用整数初始化它们）并且在数学上没有在整数类型上定义渐变，所以我无法评估它们。