你好，
我目前正在尝试计算Tensorflow 1.13.1中的渐变并使用GradientTape中解释的official documentation类，但我得到了TypeError: Fetch argument None has invalid type <class 'NoneType'>。
下面，我将包括两个简单的情况，我得到这个错误，只使用开箱即用的Tensorflow功能，第一个是更简单的最小工作示例，第二个是我实际需要解决/获得工作-周围。为了完整起见，我使用的是Python 3.6.8。
import tensorflow as tf
tf.reset_default_graph()
x = tf.constant([1., 2., 3.])
with tf.GradientTape(persistent=True) as gg:
gg.watch(x)
f1 = tf.map_fn(lambda a: a**2, x)
f2 = x*x
# Computes gradients
d_fx1 = gg.gradient(f1, x) #Line that causes the error
d_fx2 = gg.gradient(f2, x) #No error
del gg #delete persistent GradientTape
with tf.Session() as sess:
d1, d2 = sess.run((d_fx1, d_fx2))
print(d1, d2)
在此代码中，f1和f2以不同的方式计算，但给出相同的数组。但是，当试图计算与它们相关的梯度时，第一行给出以下错误，而第二行无瑕疵地工作。我在下面报告错误的堆栈跟踪
TypeError Traceback (most recent call last)
<ipython-input-1-9c59a2cf2d9b> in <module>()
15
16 with tf.Session() as sess:
---> 17 d1, d2 = sess.run((d_fx1, d_fx2))
18 print(d1, d2)
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
927 try:
928 result = self._run(None, fetches, feed_dict, options_ptr,
--> 929 run_metadata_ptr)
930 if run_metadata:
931 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1135 # Create a fetch handler to take care of the structure of fetches.
1136 fetch_handler = _FetchHandler(
-> 1137 self._graph, fetches, feed_dict_tensor, feed_handles=feed_handles)
1138
1139 # Run request and get response.
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in __init__(self, graph, fetches, feeds, feed_handles)
469 """
470 with graph.as_default():
--> 471 self._fetch_mapper = _FetchMapper.for_fetch(fetches)
472 self._fetches = []
473 self._targets = []
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in for_fetch(fetch)
259 elif isinstance(fetch, (list, tuple)):
260 # NOTE(touts): This is also the code path for namedtuples.
--> 261 return _ListFetchMapper(fetch)
262 elif isinstance(fetch, collections.Mapping):
263 return _DictFetchMapper(fetch)
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in __init__(self, fetches)
368 """
369 self._fetch_type = type(fetches)
--> 370 self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches]
371 self._unique_fetches, self._value_indices = _uniquify_fetches(self._mappers)
372
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in <listcomp>(.0)
368 """
369 self._fetch_type = type(fetches)
--> 370 self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches]
371 self._unique_fetches, self._value_indices = _uniquify_fetches(self._mappers)
372
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in for_fetch(fetch)
256 if fetch is None:
257 raise TypeError('Fetch argument %r has invalid type %r' % (fetch,
--> 258 type(fetch)))
259 elif isinstance(fetch, (list, tuple)):
260 # NOTE(touts): This is also the code path for namedtuples.
TypeError: Fetch argument None has invalid type <class 'NoneType'>
请注意，我也尝试过一次只计算一个渐变，即使用persistent=False，并得到相同的结果。
下面，我将包括最小的工作示例，以重现我得到的相同错误，但尝试解决我实际上正在处理的问题。
在这段代码中，我使用RNN计算输出w.r.t的一些输入，我需要计算输出w.r.t输入的jacobian。
import tensorflow as tf
from tensorflow.keras.layers import RNN, GRUCell
# Define size of variable. TODO: adapt to data
inp_dim = 2
num_units = 50
batch_size = 100
timesteps = 10
# Reset the graph, so as to avoid errors
tf.reset_default_graph()
# Building the model
inputs = tf.ones(shape=(timesteps, batch_size, inp_dim))
# Follow gradient computations
with tf.GradientTape() as g:
g.watch(inputs)
cells = [GRUCell(num_units), GRUCell(num_units)]
rnn = RNN(cells, time_major=True, return_sequences=True)
f = rnn(inputs)
d_fx = g.batch_jacobian(f, inputs)
# Run graph
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
grads = sess.run(d_fx)
grads.shape
关于堆栈跟踪，我得到相同的错误，但线路较少（在此堆栈跟踪中有一个for_fetch，<listcomp>和__init较少）。为了完整起见，我仍然将其包含在下面
TypeError Traceback (most recent call last)
<ipython-input-5-bb2ce4eebe87> in <module>()
25 with tf.Session() as sess:
26 sess.run(tf.global_variables_initializer())
---> 27 grads = sess.run(d_fx)
28 grads.shape
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
927 try:
928 result = self._run(None, fetches, feed_dict, options_ptr,
--> 929 run_metadata_ptr)
930 if run_metadata:
931 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1135 # Create a fetch handler to take care of the structure of fetches.
1136 fetch_handler = _FetchHandler(
-> 1137 self._graph, fetches, feed_dict_tensor, feed_handles=feed_handles)
1138
1139 # Run request and get response.
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in __init__(self, graph, fetches, feeds, feed_handles)
469 """
470 with graph.as_default():
--> 471 self._fetch_mapper = _FetchMapper.for_fetch(fetches)
472 self._fetches = []
473 self._targets = []
C:\HOMEWARE\Miniconda3-Windows-x86_64\envs\rdwsenv\lib\site-packages\tensorflow\python\client\session.py in for_fetch(fetch)
256 if fetch is None:
257 raise TypeError('Fetch argument %r has invalid type %r' % (fetch,
--> 258 type(fetch)))
259 elif isinstance(fetch, (list, tuple)):
260 # NOTE(touts): This is also the code path for namedtuples.
TypeError: Fetch argument None has invalid type <class 'NoneType'>
我觉得有一些Tensorflow功能的错误让我错误，但我不确定。最后，我感兴趣的是得到一个tensor，其中包含我的网络输出的jacobian w.r.t到输入。如何使用其他工具或更正我的代码来实现这一目标？
编辑：好的，所以我考虑了danyfang的评论，并试图调查在Github上提出的问题，他引用了tf.gradients返回None而不是0，因为在低级Tensorflow中有一些实现设计。
因此，我尝试通过计算0来创建一个简单的情况，我确信渐变与tf.matmul(tf.transpose(x), x)不同。我发布在MWE下面。
import tensorflow as tf
tf.reset_default_graph()
x = tf.constant([[1., 2., 3.]])
with tf.GradientTape(persistent=True) as gg:
gg.watch(x)
y = tf.matmul(x, tf.transpose(x))
f1 = tf.map_fn(lambda a: a, y)
# Computes gradients
d_fx1 = gg.gradient(f1, x)
d_yx = gg.gradient(y, x)
del gg #delete persistent GradientTape
with tf.Session() as sess:
#d1 = sess.run(d_fx1) # Same error None type
d2 = sess.run(d_yx) #Works flawlessly. returns array([[2., 4., 6.]], dtype=float32)
d2
这显示（至少在我看来）错误的产生不是因为这个issue报告的行为，而是另一个原因是由于较低级别的实现。
编辑：下面，我报告我如何计算输出w.r.t输出的tf.hessians。
我成功地使用函数tf.gradients计算渐变。但是，根据文档，此函数使用符号派生，而GradientTape.gradient使用自动区分。在我正在阅读的论文中，他们讨论了自动区分，所以我不知道以后我是否会遇到一些问题，但至少我的代码运行了。
下面，我发布了一个MWE，其中包含我已使用的RNN代码。
import tensorflow as tf
from tensorflow.keras.layers import RNN, GRUCell, Dense
# Define size of variable. TODO: adapt to data
inp_dim = 2
num_units = 50
batch_size = 100
timesteps = 10
# Reset the graph, so as to avoid errors
tf.reset_default_graph()
inputs = tf.ones(shape=(timesteps, batch_size, inp_dim))
### Building the model
cells = [GRUCell(num_units), GRUCell(num_units)]
rnn = RNN(cells, time_major=True, return_sequences=True)
final_layer = Dense(1, input_shape=(num_units,))
# Apply to inputs
last_state = rnn(inputs)
f = final_layer(last_state)
[derivs] = tf.gradients(f, inputs)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
grads = sess.run(derivs)
只是为了警告任何想要计算二阶导数的感兴趣的旁观者，不支持使用tf.gradients(tf.gradients(func, vars))。还有一个名为tf.hessian的函数，但是在上面的代码中用tf.gradients替换tf.hessian不起作用，导致错误很长，以至于我不会在这里包含它。我很可能会在Github上做一个问题，我会在这里链接任何感兴趣的人。目前，当我遇到一个令人不满意的解决方法时，我会将自己的回答标记为解决我的问题。
在Github上看到这个issue。