0
システム情報とValueError：RNNCellを再利用しようとすると - tensorflowにループ
Linux Ubuntu 16.04
tensorflow-gpu==1.1.0
ながら、私は非常に複雑グラフでこのエラーを取得していますが、私は以下の最小限の（うまくいけば代表）の例でそれを再現することができます：
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)
問題のトレースバックは、次のとおりです。
[email protected]:~$ 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.)
私はtensorflow 1.0 rathe使用している場合1.1より大きい場合、問題は発生しません。私はまた、スコープを削除しようとした
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?
：LSTMセルを定義するときに新しいtensorflowバージョンの
[email protected]:~$ source Repositories/tfr10/bin/activate
(tfr10) [email protected]:~$ 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) [email protected]:~$
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?
私はbuild_graph（）のwhileループと関係があると思われます。私は他の答えに従ってみましたが、このテンソルフローのループケースでは動作しませんでした。どんな助けでも大歓迎です。
すべてのTensorflowのウィザードは答えを知っていますか？
フランチェスコ