系统信息
Linux Ubuntu 16.04
tensorflow-gpu==1.1.0
我在相当复杂的图表中收到此错误，但我可以使用下面的一个最小（但希望有代表性）示例重现它：
import tensorflow as tf
import numpy as np
class Controller(object):
def __init__(self, batch_size, input_size):
self.batch_size = batch_size
self.input_size = input_size
with tf.name_scope("controller"):
self.network_vars()
self.nn_output_size = None
with tf.variable_scope("shape_inference"):
self.nn_output_size = self.get_nn_output_size()
def network_vars(self):
self.lstm_cell = tf.contrib.rnn.BasicLSTMCell(256)
self.state = self.lstm_cell.zero_state(self.batch_size, tf.float32)
def network_op(self, x, state):
x = tf.convert_to_tensor(x)
return self.lstm_cell(x, state)
def get_state(self):
return self.state
def update_state(self, new_state):
return tf.no_op()
def process_input(self, x, state=None):
nn_output, nn_state = self.network_op(x, state)
return nn_output, nn_state
def get_nn_output_size(self):
input_tensor = np.zeros([self.batch_size, self.input_size], dtype=np.float32)
output_vector, _ = self.network_op(input_tensor, self.get_state())
shape = output_vector.get_shape().as_list()
if len(shape) > 2:
raise ValueError("Expected the neural network to output a 1D vector")
else:
return shape[1]
class DNC(object):
def __init__(self, controller, batch_size, input_size):
self.controller = controller
self.batch_size = batch_size
self.input_size = input_size
self.build_graph()
def _step_op(self, x, controller_state=None):
_, nn_state = self.controller.process_input(x, controller_state)
return [nn_state[0], nn_state[1]]
def _loop_body(self, t, controller_state):
x = np.random.random_sample((self.batch_size, self.input_size)).astype(np.float32)
output_list = self._step_op(x, controller_state)
new_controller_state = tf.contrib.rnn.LSTMStateTuple(output_list[0], output_list[1])
return t+1, new_controller_state
def build_graph(self):
controller_state = self.controller.get_state()
if not isinstance(controller_state, tf.contrib.rnn.LSTMStateTuple):
controller_state = tf.contrib.rnn.LSTMStateTuple(controller_state[0], controller_state[1])
with tf.variable_scope("sequence_loop") as scope:
time = tf.constant(0, dtype=tf.int32)
final_results = tf.while_loop(
cond=lambda time, *_: time < 50,
body=self._loop_body,
loop_vars=(time, controller_state),
parallel_iterations=32,
swap_memory=True
)
if __name__ == "__main__":
batch_size = 32
input_size = 10
rnn_controller = Controller(batch_size, input_size)
dnc = DNC(rnn_controller, batch_size, input_size)
问题的追溯是：
francescoferroni@francescoferroni:~$ python controller.py
Traceback (most recent call last):
File "controller.py", line 84, in <module>
dnc = DNC(rnn_controller, batch_size, input_size)
File "controller.py", line 52, in __init__
self.build_graph()
File "controller.py", line 77, in build_graph
swap_memory=True
File "/home/francescoferroni/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2623, in while_loop
result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "/home/francescoferroni/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2456, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/home/francescoferroni/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2406, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "controller.py", line 60, in _loop_body
output_list = self._step_op(x, controller_state)
File "controller.py", line 55, in _step_op
_, nn_state = self.controller.process_input(x, controller_state)
File "controller.py", line 33, in process_input
nn_output, nn_state = self.network_op(x, state)
File "controller.py", line 24, in network_op
return self.lstm_cell(x, state)
File "/home/francescoferroni/anaconda3/lib/python3.6/site-packages/tensorflow/contrib/rnn/python/ops/core_rnn_cell_impl.py", line 235, in __call__
with _checked_scope(self, scope or "basic_lstm_cell", reuse=self._reuse):
File "/home/francescoferroni/anaconda3/lib/python3.6/contextlib.py", line 82, in __enter__
return next(self.gen)
File "/home/francescoferroni/anaconda3/lib/python3.6/site-packages/tensorflow/contrib/rnn/python/ops/core_rnn_cell_impl.py", line 77, in _checked_scope
type(cell).__name__))
ValueError: Attempt to reuse RNNCell <tensorflow.contrib.rnn.python.ops.core_rnn_cell_impl.BasicLSTMCell object at 0x7fcaeca99518> with a different variable scope than its first use. First use of cell was with scope 'shape_inference/basic_lstm_cell', this attempt is with scope 'sequence_loop/basic_lstm_cell'. Please create a new instance of the cell if you would like it to use a different set of weights. If before you were using: MultiRNNCell([BasicLSTMCell(...)] * num_layers), change to: MultiRNNCell([BasicLSTMCell(...) for _ in range(num_layers)]). If before you were using the same cell instance as both the forward and reverse cell of a bidirectional RNN, simply create two instances (one for forward, one for reverse). In May 2017, we will start transitioning this cell's behavior to use existing stored weights, if any, when it is called with scope=None (which can lead to silent model degradation, so this error will remain until then.)
如果我使用tensorflow 1.0而不是1.1，则不会引起任何问题。
francescoferroni@francescoferroni:~$ source Repositories/tfr10/bin/activate
(tfr10) francescoferroni@francescoferroni:~$ python controller.py
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.8.0 locally
(tfr10) francescoferroni@francescoferroni:~$
对于新的tensorflow版本，我在定义LSTM单元时尝试添加了reuse = True标志，但后来又出现了另一个错误：
ValueError: Variable shape_inference/basic_lstm_cell/weights does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?
我也尝试删除控制器定义中的范围。
ValueError: Variable basic_lstm_cell/weights does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?
我怀疑它与build_graph（）中的while循环有关。我尝试了其他答案，但无法使用这个tensorflow while循环案例。任何帮助将不胜感激。
任何Tensorflow向导都知道答案吗？
弗朗西斯
答案 0 :(得分：1)
我建议tf.make_template，它是变量创建的包装器，它将引用的TensorFlow变量的标识与Python模板对象绑定。修改了您的示例，我将Controller.network_op重命名为Controller._network_op_impl，然后添加Controller.__init__（只要在调用network_op之前的位置无关紧要）：
self.network_op = tf.make_template("network_op", self._network_op_impl)