我正在尝试使用TensorFlow r1.2训练带有mse损失函数的自动编码器，但我不断得到一个FailedPreconditionError，它表明与计算mse相关的其中一个变量未初始化（参见完整堆栈跟踪）打印输出如下）。我在Jupyter笔记本中运行它，我正在使用Python 3。
我将我的代码修改为一个最小的例子，如下所示
import tensorflow as tf
import numpy as np
from functools import partial
# specify network
def reset_graph(seed=0):
tf.reset_default_graph()
tf.set_random_seed(seed)
np.random.seed(seed)
reset_graph()
n_inputs = 100
n_hidden = 6
n_outputs = n_inputs
learning_rate = 0.001
l2_reg = 0.001
X = tf.placeholder(tf.float32, shape=[None, n_inputs])
he_init = tf.contrib.layers.variance_scaling_initializer()
l2_regularizer = tf.contrib.layers.l2_regularizer(l2_reg)
my_dense_layer = partial(tf.layers.dense,
activation=tf.nn.elu,
kernel_initializer=he_init,
kernel_regularizer=l2_regularizer)
hidden1 = my_dense_layer(X, n_hidden1)
outputs = my_dense_layer(hidden1, n_outputs, activation=None)
reconstruction_loss = tf.reduce_mean(tf.metrics.mean_squared_error(X, outputs))
reg_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
loss = tf.add_n([reconstruction_loss] + reg_losses)
optimizer = tf.train.AdamOptimizer(learning_rate)
training_op = optimizer.minimize(loss)
init = tf.global_variables_initializer()
# generate 1000 random examples
sample_X = np.random.rand(1000, 100)
# train network
n_epochs = 10
batch_size = 50
with tf.Session() as sess:
sess.run(init) # init.run()
for epoch in range(n_epochs):
n_batches = sample_X.shape[0] // batch_size
for iteration in range(n_batches):
start_idx = iteration*batch_size
if iteration == n_batches-1:
end_idx = sample_X.shape[0]
else:
end_idx = start_idx + batch_size
sys.stdout.flush()
X_batch = sample_X[start_idx:end_idx]
sess.run(training_op, feed_dict={X: X_batch})
loss_train = reconstruction_loss.eval(feed_dict={X: X_batch})
print(round(loss_train, 5))
当我将定义reconstruction_loss的行替换为不使用tf.metrics时，如下所示
reconstruction_loss = tf.reduce_mean(tf.square(tf.norm(outputs - X)))
我没有得到例外。
我已经检查过几个类似的SO问题，但没有一个能解决我的问题。例如，在FailedPreconditionError: Attempting to use uninitialized in Tensorflow的答案中建议的一个可能原因是未能初始化TF图中的所有变量，但我的脚本使用init = tf.global_variables_initializer()然后sess.run(init)初始化所有TF变量。另一个可能的原因是Adam优化器创建了自己的变量，需要在指定优化器后对其进行初始化（参见Tensorflow: Using Adam optimizer）。但是，我的脚本在优化器之后定义了变量初始化程序，正如在该问题的接受答案中所建议的那样，这也不是我的问题。
任何人都可以发现我的脚本有任何问题或建议尝试解决此错误的原因吗？
以下是错误的堆栈跟踪。
---------------------------------------------------------------------------
FailedPreconditionError Traceback (most recent call last)
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
1138 try:
-> 1139 return fn(*args)
1140 except errors.OpError as e:
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
1120 feed_dict, fetch_list, target_list,
-> 1121 status, run_metadata)
1122
~\AppData\Local\Continuum\Anaconda3\lib\contextlib.py in __exit__(self, type, value, traceback)
88 try:
---> 89 next(self.gen)
90 except StopIteration:
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py in raise_exception_on_not_ok_status()
465 compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466 pywrap_tensorflow.TF_GetCode(status))
467 finally:
FailedPreconditionError: Attempting to use uninitialized value mean_squared_error/total
[[Node: mean_squared_error/total/read = Identity[T=DT_FLOAT, _class=["loc:@mean_squared_error/total"], _device="/job:localhost/replica:0/task:0/cpu:0"](mean_squared_error/total)]]
During handling of the above exception, another exception occurred:
FailedPreconditionError Traceback (most recent call last)
<ipython-input-55-aac61c488ed8> in <module>()
64 sess.run(training_op, feed_dict={X: X_batch})
65
---> 66 loss_train = reconstruction_loss.eval(feed_dict={X: X_batch})
67 print(round(loss_train, 5))
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py in eval(self, feed_dict, session)
604
605 """
--> 606 return _eval_using_default_session(self, feed_dict, self.graph, session)
607
608
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py in _eval_using_default_session(tensors, feed_dict, graph, session)
3926 "the tensor's graph is different from the session's "
3927 "graph.")
-> 3928 return session.run(tensors, feed_dict)
3929
3930
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
787 try:
788 result = self._run(None, fetches, feed_dict, options_ptr,
--> 789 run_metadata_ptr)
790 if run_metadata:
791 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
995 if final_fetches or final_targets:
996 results = self._do_run(handle, final_targets, final_fetches,
--> 997 feed_dict_string, options, run_metadata)
998 else:
999 results = []
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1130 if handle is None:
1131 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1132 target_list, options, run_metadata)
1133 else:
1134 return self._do_call(_prun_fn, self._session, handle, feed_dict,
~\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
1150 except KeyError:
1151 pass
-> 1152 raise type(e)(node_def, op, message)
1153
1154 def _extend_graph(self):
FailedPreconditionError: Attempting to use uninitialized value mean_squared_error/total
[[Node: mean_squared_error/total/read = Identity[T=DT_FLOAT, _class=["loc:@mean_squared_error/total"], _device="/job:localhost/replica:0/task:0/cpu:0"](mean_squared_error/total)]]
Caused by op 'mean_squared_error/total/read', defined at:
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\__main__.py", line 3, in <module>
app.launch_new_instance()
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\traitlets\config\application.py", line 658, in launch_instance
app.start()
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 474, in start
ioloop.IOLoop.instance().start()
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 276, in dispatcher
return self.dispatch_shell(stream, msg)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 228, in dispatch_shell
handler(stream, idents, msg)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 390, in execute_request
user_expressions, allow_stdin)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 501, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2698, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2802, in run_ast_nodes
if self.run_code(code, result):
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2862, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-55-aac61c488ed8>", line 32, in <module>
reconstruction_loss = tf.reduce_mean(tf.metrics.mean_squared_error(X, outputs))
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\metrics_impl.py", line 1054, in mean_squared_error
updates_collections, name or 'mean_squared_error')
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\metrics_impl.py", line 331, in mean
total = _create_local('total', shape=[])
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\metrics_impl.py", line 196, in _create_local
validate_shape=validate_shape)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1679, in variable
caching_device=caching_device, name=name, dtype=dtype)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\variables.py", line 200, in __init__
expected_shape=expected_shape)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\variables.py", line 319, in _init_from_args
self._snapshot = array_ops.identity(self._variable, name="read")
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 1303, in identity
result = _op_def_lib.apply_op("Identity", input=input, name=name)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "C:\Users\user\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in __init__
self._traceback = _extract_stack()
FailedPreconditionError (see above for traceback): Attempting to use uninitialized value mean_squared_error/total
[[Node: mean_squared_error/total/read = Identity[T=DT_FLOAT, _class=["loc:@mean_squared_error/total"], _device="/job:localhost/replica:0/task:0/cpu:0"](mean_squared_error/total)]]
答案 0 :(得分：1)
看起来你在初始化时做的一切正常，所以我怀疑你的错误是你错误地使用了tf.metrics.mean_squared_error。
类的metrics包允许您计算一个值，但也会在多次调用sess.run时累积该值。请注意文档中的tf.metrics.mean_square_error的返回值：
https://www.tensorflow.org/api_docs/python/tf/metrics/mean_squared_error
您回复 mean_square_error，正如您所期望的那样，以及update_op。 update_op的目的是要求tensorflow计算update_op并累积均方误差。每次拨打mean_square_error，您都会获得累计值。如果要重置值，则运行sess.run(tf.local_variables_initializer())（注意本地而非全局以清除“本地”变量，因为度量包定义了它们。）
我认为度量标准包不是按照您使用它的方式使用的。我认为您的目的是仅根据当前批次计算mse作为损失，而不是在多次调用中累计值。我甚至不确定这样的积累值对差异化是如何起作用的。
所以我认为你的问题的答案是：不要以这种方式使用指标包。使用度量标准进行报告，并在测试数据集的多次迭代中累积结果，例如，不用于生成损失函数。
我认为您的意思是tf.losses.mean_squared_error