系统信息 -操作系统平台和发行版：Linux Manjaro Illyria 18.0.3 -移动设备：如果问题发生在移动设备上：与移动设备无关 -从以下位置安装TensorFlow：二进制 -TensorFlow版本：（'v1.12.0-0-ga6d8ffae09'，'1.12.0'） -Python版本：2.7.15 -CUDA / cuDNN版本：无CUDA -GPU模型和内存：无计算GPU
描述当前行为 我正在尝试将tf.contrib.rnn.AttentionCellWrapper添加到tf.nn.rnn_cell.GRUCell。在添加包装器之前，程序将完全正常运行。添加包装器后，程序将报告错误，显示在下面的回溯中。
错误Tensor objects are only iterable when eager execution is enabled使我感到困惑，因为我尝试启用急切的执行，并且结果相同。
我已将GRUCell更改为LSMMCell或其他与RNN相关的Cell，结果是相同的。
我尝试了多个tensorflow版本，结果是相同的。
我正在修改的代码与this code相同，而我正在尝试的是在126至127行之间添加AttentionCellWrapper。
描述预期的行为 该程序应该运行正常，没有任何错误。与普通代码相比，我所做的所有更改都是添加了AttentionCellWrapper。 官方文档也没有解释此错误的原因。
重现问题的代码 如上所述，带有AttentionCellWrapper的常规代码以及触发错误的函数如下。完整的代码还涵盖了repo中的其他文件。
def build_model(self):
self.X = tf.placeholder(tf.int32, [self.batch_size], name='input')
self.Y = tf.placeholder(tf.int32, [self.batch_size], name='output')
self.state = [tf.placeholder(tf.float32, [self.batch_size, self.rnn_size], name='rnn_state') for _ in xrange(self.layers)]
self.global_step = tf.Variable(0, name='global_step', trainable=False)
with tf.variable_scope('gru_layer'):
sigma = self.sigma if self.sigma != 0 else np.sqrt(6.0 / (self.n_items + self.rnn_size))
if self.init_as_normal:
initializer = tf.random_normal_initializer(mean=0, stddev=sigma)
else:
initializer = tf.random_uniform_initializer(minval=-sigma, maxval=sigma)
embedding = tf.get_variable('embedding', [self.n_items, self.rnn_size], initializer=initializer)
softmax_W = tf.get_variable('softmax_w', [self.n_items, self.rnn_size], initializer=initializer)
softmax_b = tf.get_variable('softmax_b', [self.n_items], initializer=tf.constant_initializer(0.0))
cell = rnn_cell.GRUCell(self.rnn_size, activation=self.hidden_act)
attn_cell = tf.contrib.rnn.AttentionCellWrapper(cell, attn_length=20) # state_is_tuple is True by default
drop_cell = rnn_cell.DropoutWrapper(attn_cell, output_keep_prob=self.dropout_p_hidden)
stacked_cell = rnn_cell.MultiRNNCell([drop_cell] * self.layers)
inputs = tf.nn.embedding_lookup(embedding, self.X)
output, state = stacked_cell(inputs, tuple(self.state))
self.final_state = state
if self.is_training:
'''
Use other examples of the minibatch as negative samples.
'''
sampled_W = tf.nn.embedding_lookup(softmax_W, self.Y)
sampled_b = tf.nn.embedding_lookup(softmax_b, self.Y)
logits = tf.matmul(output, sampled_W, transpose_b=True) + sampled_b
self.yhat = self.final_activation(logits)
self.cost = self.loss_function(self.yhat)
else:
logits = tf.matmul(output, softmax_W, transpose_b=True) + softmax_b
self.yhat = self.final_activation(logits)
if not self.is_training:
return
self.lr = tf.maximum(1e-5,tf.train.exponential_decay(self.learning_rate, self.global_step, self.decay_steps, self.decay, staircase=True))
'''
Try different optimizers.
'''
#optimizer = tf.train.AdagradOptimizer(self.lr)
optimizer = tf.train.AdamOptimizer(self.lr)
#optimizer = tf.train.AdadeltaOptimizer(self.lr)
#optimizer = tf.train.RMSPropOptimizer(self.lr)
tvars = tf.trainable_variables()
gvs = optimizer.compute_gradients(self.cost, tvars)
if self.grad_cap > 0:
capped_gvs = [(tf.clip_by_norm(grad, self.grad_cap), var) for grad, var in gvs]
else:
capped_gvs = gvs
self.train_op = optimizer.apply_gradients(capped_gvs, global_step=self.global_step)
其他信息/日志 包括任何有助于诊断问题的日志或源代码。如果包括回溯，请包括完整的回溯。大的日志和文件应该附加。
Traceback (most recent call last):
File "/home/syh/.local/share/JetBrains/Toolbox/apps/PyCharm-P/ch-0/183.5429.31/helpers/pydev/pydevd.py", line 1741, in <module>
main()
File "/home/syh/.local/share/JetBrains/Toolbox/apps/PyCharm-P/ch-0/183.5429.31/helpers/pydev/pydevd.py", line 1735, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "/home/syh/.local/share/JetBrains/Toolbox/apps/PyCharm-P/ch-0/183.5429.31/helpers/pydev/pydevd.py", line 1135, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/GRU4Rec_TensorFlow-master/main.py", line 86, in <module>
gru4rec = model.GRU4Rec(sess, args)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/GRU4Rec_TensorFlow-master/model.py", line 72, in __init__
self.build_model()
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/GRU4Rec_TensorFlow-master/model.py", line 142, in build_model
output, state = multi_cell(inputs, tuple(self.state))
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 233, in __call__
return super(RNNCell, self).__call__(inputs, state)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 374, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 757, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1486, in call
cur_inp, new_state = cell(cur_inp, cur_state)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1282, in __call__
output, new_state = self._cell(inputs, state, scope=scope)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 233, in __call__
return super(RNNCell, self).__call__(inputs, state)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 374, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 757, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/contrib/rnn/python/ops/rnn_cell.py", line 1190, in call
state, attns, attn_states = state
File "/run/media/syh/0D11080D0D11080D/workspace/Recommender-System/exp/venv/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 459, in __iter__
"Tensor objects are only iterable when eager execution is "
TypeError: Tensor objects are only iterable when eager execution is enabled. To iterate over this tensor use tf.map_fn.
state：<type 'tuple'>: (<tf.Tensor 'rnn_state:0' shape=(50, 100) dtype=float32>,)
__len__ = 1
state由该语句output, state = multi_cell(inputs, tuple(self.state))返回
哪里
self.state = [tf.placeholder(tf.float32, [self.batch_size, self.rnn_size], name='rnn_state') for _ in xrange(self.layers)]
multi_cell = rnn_cell.MultiRNNCell([cell] * self.layers)
inputs = tf.nn.embedding_lookup(embedding, self.X)
state由class RNNCell在tensorflow/python/ops/rnn_cell_impl.py中创建
但是，我看不到state是通过调试器由类RNNCell中的哪个语句创建的。
将tensorflow版本更新为1.13.1后，此问题仍然存在。