BasicRNNCell 如何确定单元状态大小和单元输出大小？

Question

考虑以下代码：

import tensorflow as tf
cell=tf.contrib.rnn.BasicRNNCell(num_units = rnn_size)
output, state = tf.nn.dynamic_rnn(cell, input, dtype=tf.float32)

根据 documentation of dynamic_rnn，output 和 state 的形状分别为 [batch_size, max_time, cell.output_size] 和 [batch_size, cell.state_size]。

问题：cell.state_size和cell.output_size是如何在BasicRNNCell中确定的？ BasicRNNCell的initilizer中的num_units = rnn_size与其state_size和output_size有什么关系？

Answer 1

在BasicRNNCell的情况下，您提到的所有数量都是相同的（参考code）：

 class BasicRNNCell(RNNCell):
     """The most basic RNN cell.

     Args:
      num_units: int, The number of units in the LSTM cell.
      activation: Nonlinearity to use.  Default: `tanh`.
      reuse: (optional) Python boolean describing whether to reuse variables

       in an existing scope.  If not `True`, and the existing scope already has
       the given variables, an error is raised.
     """

  def __init__(self, num_units, activation=None, reuse=None):
    super(BasicRNNCell, self).__init__(_reuse=reuse)
    self._num_units = num_units
    self._activation = activation or math_ops.tanh

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

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

BasicRNNCell 如何确定单元状态大小和单元输出大小？

How the cell state size and cell output size is determined in BasicRNNCell?

python

tensorflow

recurrent-neural-network