Machine learning 张量流。从BasicRNNCell切换到LSTMCell

我已经用BasicRNN构建了一个RNN，现在我想使用LSTMCell，但是这段话看起来并不琐碎。我应该换什么

首先，我定义所有占位符和变量：

X_placeholder = tf.placeholder(tf.float32, [batch_size, truncated_backprop_length, embedding_size])
Y_placeholder = tf.placeholder(tf.int32, [batch_size, truncated_backprop_length])

init_state = tf.placeholder(tf.float32, [batch_size, state_size])

W = tf.Variable(np.random.rand(state_size, num_classes),dtype=tf.float32)
b = tf.Variable(np.zeros((batch_size, num_classes)), dtype=tf.float32)

W2 = tf.Variable(np.random.rand(state_size, num_classes),dtype=tf.float32)
b2 = tf.Variable(np.zeros((batch_size, num_classes)), dtype=tf.float32)

然后我打开标签：

labels_series = tf.transpose(batchY_placeholder)
labels_series = tf.unstack(batchY_placeholder, axis=1)
inputs_series = X_placeholder

然后我定义我的RNN：

cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple = False)
states_series, current_state = tf.nn.dynamic_rnn(cell, inputs_series, initial_state = init_state)

我得到的错误是：

InvalidArgumentError                      Traceback (most recent call last)
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in _call_cpp_shape_fn_impl(op, input_tensors_needed, input_tensors_as_shapes_needed, debug_python_shape_fn, require_shape_fn)
    669           node_def_str, input_shapes, input_tensors, input_tensors_as_shapes,

--> 670           status)
    671   except errors.InvalidArgumentError as err:

/home/deepnlp2017/anaconda3/lib/python3.5/contextlib.py in __exit__(self, type, value, traceback)
     65             try:
---> 66                 next(self.gen)
     67             except StopIteration:

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
    468           compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 469           pywrap_tensorflow.TF_GetCode(status))
    470   finally:

InvalidArgumentError: Dimensions must be equal, but are 50 and 100 for 'rnn/while/basic_lstm_cell/mul' (op: 'Mul') with input shapes: [32,50], [32,100].

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
<ipython-input-19-2ac617f4dde4> in <module>()
      4 #cell = tf.contrib.rnn.BasicRNNCell(state_size)
      5 cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple = False)
----> 6 states_series, current_state = tf.nn.dynamic_rnn(cell, inputs_series, initial_state = init_state)

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in dynamic_rnn(cell, inputs, sequence_length, initial_state, dtype, parallel_iterations, swap_memory, time_major, scope)
    543         swap_memory=swap_memory,
    544         sequence_length=sequence_length,
--> 545         dtype=dtype)
    546 
    547     # Outputs of _dynamic_rnn_loop are always shaped [time, batch, depth].

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in _dynamic_rnn_loop(cell, inputs, initial_state, parallel_iterations, swap_memory, sequence_length, dtype)
    710       loop_vars=(time, output_ta, state),
    711       parallel_iterations=parallel_iterations,
--> 712       swap_memory=swap_memory)
    713 
    714   # Unpack final output if not using output tuples.

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in while_loop(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, name)
   2624     context = WhileContext(parallel_iterations, back_prop, swap_memory, name)
   2625     ops.add_to_collection(ops.GraphKeys.WHILE_CONTEXT, context)
-> 2626     result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
   2627     return result
   2628 

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in BuildLoop(self, pred, body, loop_vars, shape_invariants)
   2457       self.Enter()
   2458       original_body_result, exit_vars = self._BuildLoop(
-> 2459           pred, body, original_loop_vars, loop_vars, shape_invariants)
   2460     finally:
   2461       self.Exit()

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in _BuildLoop(self, pred, body, original_loop_vars, loop_vars, shape_invariants)
   2407         structure=original_loop_vars,
   2408         flat_sequence=vars_for_body_with_tensor_arrays)
-> 2409     body_result = body(*packed_vars_for_body)
   2410     if not nest.is_sequence(body_result):
   2411       body_result = [body_result]

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in _time_step(time, output_ta_t, state)
    695           skip_conditionals=True)
    696     else:
--> 697       (output, new_state) = call_cell()
    698 
    699     # Pack state if using state tuples

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in <lambda>()
    681 
    682     input_t = nest.pack_sequence_as(structure=inputs, flat_sequence=input_t)
--> 683     call_cell = lambda: cell(input_t, state)
    684 
    685     if sequence_length is not None:

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/contrib/rnn/python/ops/core_rnn_cell_impl.py in __call__(self, inputs, state, scope)
    182       i, j, f, o = array_ops.split(value=concat, num_or_size_splits=4, axis=1)
    183 
--> 184       new_c = (c * sigmoid(f + self._forget_bias) + sigmoid(i) *
    185                self._activation(j))
    186       new_h = self._activation(new_c) * sigmoid(o)

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py in binary_op_wrapper(x, y)
    882       if not isinstance(y, sparse_tensor.SparseTensor):
    883         y = ops.convert_to_tensor(y, dtype=x.dtype.base_dtype, name="y")
--> 884       return func(x, y, name=name)
    885 
    886   def binary_op_wrapper_sparse(sp_x, y):

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py in _mul_dispatch(x, y, name)
   1103   is_tensor_y = isinstance(y, ops.Tensor)
   1104   if is_tensor_y:
-> 1105     return gen_math_ops._mul(x, y, name=name)
   1106   else:
   1107     assert isinstance(y, sparse_tensor.SparseTensor)  # Case: Dense * Sparse.

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py in _mul(x, y, name)
   1623     A `Tensor`. Has the same type as `x`.
   1624   """
-> 1625   result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
   1626   return result
   1627 

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py in apply_op(self, op_type_name, name, **keywords)
    761         op = g.create_op(op_type_name, inputs, output_types, name=scope,
    762                          input_types=input_types, attrs=attr_protos,
--> 763                          op_def=op_def)
    764         if output_structure:
    765           outputs = op.outputs

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in create_op(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_shapes, compute_device)
   2395                     original_op=self._default_original_op, op_def=op_def)
   2396     if compute_shapes:
-> 2397       set_shapes_for_outputs(ret)
   2398     self._add_op(ret)
   2399     self._record_op_seen_by_control_dependencies(ret)

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in set_shapes_for_outputs(op)
   1755       shape_func = _call_cpp_shape_fn_and_require_op
   1756 
-> 1757   shapes = shape_func(op)
   1758   if shapes is None:
   1759     raise RuntimeError(

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in call_with_requiring(op)
   1705 
   1706   def call_with_requiring(op):
-> 1707     return call_cpp_shape_fn(op, require_shape_fn=True)
   1708 
   1709   _call_cpp_shape_fn_and_require_op = call_with_requiring

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in call_cpp_shape_fn(op, input_tensors_needed, input_tensors_as_shapes_needed, debug_python_shape_fn, require_shape_fn)
    608     res = _call_cpp_shape_fn_impl(op, input_tensors_needed,
    609                                   input_tensors_as_shapes_needed,
--> 610                                   debug_python_shape_fn, require_shape_fn)
    611     if not isinstance(res, dict):
    612       # Handles the case where _call_cpp_shape_fn_impl calls unknown_shape(op).

/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in _call_cpp_shape_fn_impl(op, input_tensors_needed, input_tensors_as_shapes_needed, debug_python_shape_fn, require_shape_fn)
    673       missing_shape_fn = True
    674     else:
--> 675       raise ValueError(err.message)
    676 
    677   if missing_shape_fn:

ValueError: Dimensions must be equal, but are 50 and 100 for 'rnn/while/basic_lstm_cell/mul' (op: 'Mul') with input shapes: [32,50], [32,100].

InvalidArgumentError回溯（最近一次调用上次）
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/common\u shapes.py in\u call\u cpp\u shape\u fn\u impl（op，输入所需张量，输入所需张量，调试python\u shape\u fn，需要形状）
669节点定义、输入形状、输入张量、输入张量作为形状，
-->（670状态）
671错误除外。InvalidArgumentError作为错误：
/home/deepnlp2017/anaconda3/lib/python3.5/contextlib.py in____________（自我、类型、值、回溯）
65尝试：
--->66下一个（self.gen）
67除停止迭代外：
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/errors\u impl.py在raise\u exception\u on\u not\u ok\u status（）中
468兼容as_文本（pywrap_tensorflow.TF_消息（状态）），
-->469 pywrap_tensorflow.TF_GetCode（状态））
470最后：
InvalidArgumentError：尺寸必须相等，但对于输入形状为[32,50]，[32100]的“rnn/while/basic_lstm_cell/mul”（op:“mul”）而言，尺寸分别为50和100。
在处理上述异常期间，发生了另一个异常：
ValueError回溯（最近一次调用上次）
在（）
4#单元=tf.contrib.rnn.basicrncell（状态大小）
5 cell=tf.contrib.rnn.BasicLSTMCell（state\u size，state\u为\u tuple=False）
---->6状态\u序列，当前\u状态=tf.nn.dynamic\u rnn（单元，输入\u序列，初始\u状态=初始\u状态）
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py（单元格、输入、序列长度、初始状态、数据类型、并行迭代、交换内存、时间、范围）
543交换内存=交换内存，
544序列长度=序列长度，
-->545数据类型=数据类型）
546
547#动态循环的输出总是成形的[时间、批次、深度]。
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in\u dynamic\u rnn\u循环（单元、输入、初始状态、并行迭代、交换内存、序列长度、数据类型）
710循环变量=（时间、输出、状态），
711并行迭代=并行迭代，
-->712交换内存=交换内存）
713
714#如果不使用输出元组，则解压缩最终输出。
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control\u flow\u ops.py在while\u循环中（cond、body、loop\u vars、shape\u不变量、并行迭代、back\u prop、swap\u memory、name）
2624 context=WhileContext（并行迭代、备份、交换内存、名称）
2625 ops.将_添加到_集合（ops.GraphKeys.WHILE_CONTEXT，CONTEXT）
->2626 result=context.BuildLoop（条件、主体、循环变量、形状不变量）
2627返回结果
2628
/BuildLoop中的home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py（self、pred、body、loop_vars、shape_不变量）
2457 self.Enter（）
2458原始\u body\u结果，退出\u vars=self.\u BuildLoop(
->2459 pred，主体，原始循环变量，循环变量，形状不变量）
2460最后：
2461自我退出（）
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/control\u flow\u ops.py in\u BuildLoop（self、pred、body、original\u loop\u vars、loop\u vars、shape\u不变量）
2407结构=原始循环变量，
2408平面\u序列=变量\u用于\u体\u与\u张量\u阵列）
->2409阀体结果=阀体（*阀体的封装变量）
2410如果不是嵌套。是\u序列（正文\u结果）：
2411 body_result=[body_result]
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in\u time\u step（时间、输出、状态）
695跳过（条件=真）
696其他：
-->697（输出，新状态）=调用单元（）
698
699#使用状态元组时打包状态
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py in（）
681
682输入\u t=nest.pack\u sequence\u as（结构=输入，平坦\u sequence=input\u t）
-->683调用单元=λ：单元（输入，状态）
684
685如果序列长度不是无：
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/contrib/rnn/python/ops/core\u rnn\u cell\u impl.py in\uuuuuu调用（self、input、state、scope）
182 i，j，f，o=数组操作拆分（值=concat，num或大小拆分=4，轴=1）
183
-->184新的c=（c*sigmoid（f+self.\u忘记_偏见）+sigmoid（i）*
185自激活（j））
186新h=自激活（新c）*乙状结肠（o）
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py二进制_op_包装（x，y）
882如果不存在（y，稀疏张量，稀疏传感器）：
883 y=ops.convert_to_tensor（y，dtype=x.dtype.base_dtype，name=“y”）
-->884返回函数（x，y，name=name）
885
886 def二进制文件（sp_x，y）：
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/math\u ops.py in\u mul\u dispatch（x，y，name）
1103是张量（y，运算张量）
1104如果是张量：
->1105返回gen\u math\u ops.\u mul（x，y，name=name）
1106其他：
1107断言存在（y，稀疏张量。稀疏传感器）#情况：稠密*稀疏。
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py in_mul（x，y，name）
1623 A‘张量’。与“x”的类型相同。
1624   """
->1625结果=_op_def_lib.apply_op（“Mul”，x=x，y=y，name=name）
1626返回结果
1627
/home/deepnlp2017/.local/lib/python3.5/site-packages/tensorflow/python/framework/o
cell = tf.contrib.rnn.BasicLSTMCell(state_size, state_is_tuple=False)

init_state = cell.zero_state(batch_size, dtype)