Tensorflow LSTM闸门重量

Question

你好，我有一个关于张量流的问题。我训练了一些LSTM模型，我可以获得突触连接的权重和偏差，但是我似乎无法访问LSTM细胞的输入、新输入、输出和忘记门权重。我可以得到门张量，但当我在一个会话中尝试.eval（）它们时，我会出错。我使用的是在tensorflow/python/ops/rnn中找到的basiclstmell类_细胞.py对于我的网络

`

class BasicLSTMCell(RNNCell):
  """Basic LSTM recurrent network cell.

  The implementation is based on: http://arxiv.org/abs/1409.2329.

  We add forget_bias (default: 1) to the biases of the forget gate in order to
  reduce the scale of forgetting in the beginning of the training.

  It does not allow cell clipping, a projection layer, and does not
  use peep-hole connections: it is the basic baseline.

  For advanced models, please use the full LSTMCell that follows.
  """

  def __init__(self, num_units, forget_bias=1.0, input_size=None,
               state_is_tuple=True, activation=tanh):
    """Initialize the basic LSTM cell.

    Args:
      num_units: int, The number of units in the LSTM cell.
      forget_bias: float, The bias added to forget gates (see above).
      input_size: Deprecated and unused.
      state_is_tuple: If True, accepted and returned states are 2-tuples of
        the `c_state` and `m_state`.  If False, they are concatenated
        along the column axis.  The latter behavior will soon be deprecated.
      activation: Activation function of the inner states.
    """
    if not state_is_tuple:
      logging.warn("%s: Using a concatenated state is slower and will soon be "
                   "deprecated.  Use state_is_tuple=True.", self)
    if input_size is not None:
      logging.warn("%s: The input_size parameter is deprecated.", self)
    self._num_units = num_units
    self._forget_bias = forget_bias
    self._state_is_tuple = state_is_tuple
    self._activation = activation

  @property
  def state_size(self):
    return (LSTMStateTuple(self._num_units, self._num_units)
            if self._state_is_tuple else 2 * self._num_units)

  @property
  def output_size(self):
    return self._num_units

  def __call__(self, inputs, state, scope=None):
    """Long short-term memory cell (LSTM)."""
    with vs.variable_scope(scope or type(self).__name__):  # "BasicLSTMCell"
      # Parameters of gates are concatenated into one multiply for efficiency.
      if self._state_is_tuple:
        c, h = state
      else:
        c, h = array_ops.split(1, 2, state)
      concat = _linear([inputs, h], 4 * self._num_units, True)

      # i = input_gate, j = new_input, f = forget_gate, o = output_gate
      i, j, f, o = array_ops.split(1, 4, concat)

      new_c = (c * sigmoid(f + self._forget_bias) + sigmoid(i) *
               self._activation(j))
      new_h = self._activation(new_c) * sigmoid(o)

      if self._state_is_tuple:
        new_state = LSTMStateTuple(new_c, new_h)
      else:
        new_state = array_ops.concat(1, [new_c, new_h])
      return new_h, new_state


def _get_concat_variable(name, shape, dtype, num_shards):
  """Get a sharded variable concatenated into one tensor."""
  sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
  if len(sharded_variable) == 1:
    return sharded_variable[0]

  concat_name = name + "/concat"
  concat_full_name = vs.get_variable_scope().name + "/" + concat_name + ":0"
  for value in ops.get_collection(ops.GraphKeys.CONCATENATED_VARIABLES):
    if value.name == concat_full_name:
      return value

  concat_variable = array_ops.concat(0, sharded_variable, name=concat_name)
  ops.add_to_collection(ops.GraphKeys.CONCATENATED_VARIABLES,
                        concat_variable)
  return concat_variable


def _get_sharded_variable(name, shape, dtype, num_shards):
  """Get a list of sharded variables with the given dtype."""
  if num_shards > shape[0]:
    raise ValueError("Too many shards: shape=%s, num_shards=%d" %
                     (shape, num_shards))
  unit_shard_size = int(math.floor(shape[0] / num_shards))
  remaining_rows = shape[0] - unit_shard_size * num_shards

  shards = []
  for i in range(num_shards):
    current_size = unit_shard_size
    if i < remaining_rows:
      current_size += 1
    shards.append(vs.get_variable(name + "_%d" % i, [current_size] + shape[1:],
                                  dtype=dtype))
  return shards

`

我可以看到在def调用中使用的I，j，f，o门tf.打印当我在一个会话中尝试.eval（）它们时，我会得到错误。我也试过了tf.getVariable但无法提取权重矩阵。我的问题：有没有一种方法来评估i，j，f和o门权重/矩阵？在

Answer 1

首先，澄清一些混淆：i、j、f和o张量不是权重矩阵；它们是依赖于特定LSTM单元输入的中间计算步骤。LSTM单元的所有权值都存储在变量self.\u kernel and self.\u bias中，并且存储在一个常量self.\u forget_bias中。在

所以，为了回答你的问题的两种可能的解释，我将展示如何打印self.\u kernel和self.\u bias的值，以及每一步I，j，f和o张量的值。在

假设我们有下图：

import numpy as np
import tensorflow as tf

timesteps = 7
num_input = 4
num_units = 3
x_val = np.random.normal(size=(1, timesteps, num_input))

lstm = tf.nn.rnn_cell.BasicLSTMCell(num_units = num_units)
X = tf.placeholder("float", [1, timesteps, num_input])
inputs = tf.unstack(X, timesteps, 1)
outputs, state = tf.contrib.rnn.static_rnn(lstm, inputs, dtype=tf.float32)

如果我们知道任何张量的名称，我们就可以找到它的值。找到张量名称的一种方法是查看张量板。在

^{pr2}$

现在我们可以通过终端命令启动TensorBoard

tensorboard  logdir=graph  host=localhost 

并发现产生i，j，f，o张量的运算名为“rnn/basic_lstm_cell/split”，而kernel和bias分别称为“rnn/basic_lstm_cell/kernel”和“rnn/basic_lstm_cell/bias”：

在tf.contrib.rnn公司.static\u rnn函数调用我们的基本lstm单元7次，每次调用一次。当Tensorflow被要求在同一名称下创建多个操作时，它会为它们添加后缀，如下所示： rnn/基本单元/分割， rnn/基本单元/分割单元1， ..., rnn/基本单元/分割单元6。 这些是我们行动的名称。在

tensorflow中张量的名称由产生张量的操作的名称组成，后跟冒号，后跟产生此张量的操作输出的索引。Kernel和bias ops只有一个输出，因此张量名称为

kernel = graph.get_tensor_by_name("rnn/basic_lstm_cell/kernel:0")
bias = graph.get_tensor_by_name("rnn/basic_lstm_cell/bias:0")

拆分操作产生四个输出：i、j、f和o，因此这些张量的名称为：

i_list = []
j_list = []
f_list = []
o_list = []
for suffix in ["", "_1", "_2", "_3", "_4", "_5", "_6"]:   
    i_list.append(graph.get_tensor_by_name(
        "rnn/basic_lstm_cell/split{}:0".format(suffix)
    ))
    j_list.append(graph.get_tensor_by_name(
        "rnn/basic_lstm_cell/split{}:1".format(suffix)
    ))
    f_list.append(graph.get_tensor_by_name(
        "rnn/basic_lstm_cell/split{}:2".format(suffix)
    ))        
    o_list.append(graph.get_tensor_by_name(
        "rnn/basic_lstm_cell/split{}:3".format(suffix)
    ))

现在我们可以找到所有张量的值：

    with tf.Session(graph=graph) as sess:
        train_writer = tf.summary.FileWriter('./graph', sess.graph)
        sess.run(init)
        weights = sess.run([kernel, bias])
        print("Weights:\n", weights)
        i_values, j_values, f_values, o_values = sess.run([i_list, j_list, f_list, o_list], 
                                                          feed_dict = {X:x_val})
        print("i values:\n", i_values)
        print("j values:\n", j_values)
        print("f_values:\n", f_values)
        print("o_values:\n", o_values)

或者，我们可以通过查看图中所有张量的列表来找到张量名称，可以通过以下方式生成：

tensors_per_node = [node.values() for node in graph.get_operations()]
tensor_names = [tensor.name for tensors in tensors_per_node for tensor in tensors]
print(tensor_names)

或者，对于所有操作的简短列表：

print([node.name for node in graph.get_operations()])

第三种方法是读取source code并找出哪些名称被分配给哪些张量。在