获取TensorFlow中dynamic_rnn的最后一个输出

Question

我有一个3-D张量的形状[batch, None, dim] ，其中第二个维度，即时间步长，是未知的。 我使用dynamic_rnn来处理这样的输入，如下面的代码片段所示：

import numpy as np
import tensorflow as tf

batch = 2
dim = 3
hidden = 4

lengths = tf.placeholder(dtype=tf.int32, shape=[batch])
inputs = tf.placeholder(dtype=tf.float32, shape=[batch, None, dim])
cell = tf.nn.rnn_cell.GRUCell(hidden)
cell_state = cell.zero_state(batch, tf.float32)
output, _ = tf.nn.dynamic_rnn(cell, inputs, lengths, initial_state=cell_state)

实际上，运行这个剪切了一些实际数字，我有一些合理的结果：

inputs_ = np.asarray([[[0, 0, 0], [1, 1, 1], [2, 2, 2], [3, 3, 3]],
                    [[6, 6, 6], [7, 7, 7], [8, 8, 8], [9, 9, 9]]],
                    dtype=np.int32)
lengths_ = np.asarray([3, 1], dtype=np.int32)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    output_ = sess.run(output, {inputs: inputs_, lengths: lengths_})
    print(output_)

输出是：

[[[ 0.          0.          0.          0.        ]
  [ 0.02188676 -0.01294564  0.05340237 -0.47148666]
  [ 0.0343586  -0.02243731  0.0870839  -0.89869428]
  [ 0.          0.          0.          0.        ]]

 [[ 0.00284752 -0.00315077  0.00108094 -0.99883419]
  [ 0.          0.          0.          0.        ]
  [ 0.          0.          0.          0.        ]
  [ 0.          0.          0.          0.        ]]]

有没有办法用动态RNN的最后一个相关输出得到形状的3-D张量[batch, 1, hidden] ？ 谢谢！

Answer 1

这就是gather_nd的用途！

def extract_axis_1(data, ind):
    """
    Get specified elements along the first axis of tensor.
    :param data: Tensorflow tensor that will be subsetted.
    :param ind: Indices to take (one for each element along axis 0 of data).
    :return: Subsetted tensor.
    """

    batch_range = tf.range(tf.shape(data)[0])
    indices = tf.stack([batch_range, ind], axis=1)
    res = tf.gather_nd(data, indices)

    return res

在你的情况下：

output = extract_axis_1(output, lengths - 1)

现在output是维度的张量[batch_size, num_cells] 。

Answer 2

从以下两个来源，

http://www.wildml.com/2016/08/rnns-in-tensorflow-a-practical-guide-and-undocumented-features/

outputs, last_states = tf.nn.dynamic_rnn(
cell=cell,
dtype=tf.float64,
sequence_length=X_lengths,
inputs=X)

或者https://github.com/ageron/handson-ml/blob/master/14_recurrent_neural_networks.ipynb ,

很明显，last_states可以直接从dynamic_rnn调用的SECOND输出中提取。 它将为您提供跨所有层的last_states（在LSTM中它是从LSTMStateTuple编译的），而输出包含最后一层中的所有状态。

Answer 3

好的 - 所以，看起来实际上有一个更简单的解决方案。 正如@Shao Tang和@Rahul所提到的，执行此操作的首选方法是访问最终的单元状态。 原因如下：

• 如果你看一下GRUCell源代码（下面），你会发现单元格维护的“状态”实际上是隐藏权重本身。 因此，当tf.nn.dynamic_rnn返回最终状态时，它实际上会返回您感兴趣的最终隐藏权重。为了证明这一点，我只是调整了您的设置并获得了结果：

GRUCell Call（rnn_cell_impl.py）：

def call(self, inputs, state):
"""Gated recurrent unit (GRU) with nunits cells."""
if self._gate_linear is None:
      bias_ones = self._bias_initializer
if self._bias_initializer is None:
        bias_ones = init_ops.constant_initializer(1.0, dtype=inputs.dtype)
with vs.variable_scope("gates"):  # Reset gate and update gate.
self._gate_linear = _Linear(
            [inputs, state],
2 * self._num_units,
True,
bias_initializer=bias_ones,
kernel_initializer=self._kernel_initializer)
    value = math_ops.sigmoid(self._gate_linear([inputs, state]))
    r, u = array_ops.split(value=value, num_or_size_splits=2, axis=1)
    r_state = r * state
if self._candidate_linear is None:
with vs.variable_scope("candidate"):
self._candidate_linear = _Linear(
            [inputs, r_state],
self._num_units,
True,
bias_initializer=self._bias_initializer,
kernel_initializer=self._kernel_initializer)
    c = self._activation(self._candidate_linear([inputs, r_state]))
    new_h = u * state + (1 - u) * c
return new_h, new_h

解：

import numpy as np
import tensorflow as tf

batch = 2
dim = 3
hidden = 4

lengths = tf.placeholder(dtype=tf.int32, shape=[batch])
inputs = tf.placeholder(dtype=tf.float32, shape=[batch, None, dim])
cell = tf.nn.rnn_cell.GRUCell(hidden)
cell_state = cell.zero_state(batch, tf.float32)
output, state = tf.nn.dynamic_rnn(cell, inputs, lengths, initial_state=cell_state)

inputs_ = np.asarray([[[0, 0, 0], [1, 1, 1], [2, 2, 2], [3, 3, 3]],
                    [[6, 6, 6], [7, 7, 7], [8, 8, 8], [9, 9, 9]]],
                    dtype=np.int32)
lengths_ = np.asarray([3, 1], dtype=np.int32)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    output_, state_ = sess.run([output, state], {inputs: inputs_, lengths: lengths_})
    print (output_)
    print (state_)

输出：

[[[ 0.          0.          0.          0.        ]
  [-0.24305521 -0.15512943  0.06614969  0.16873555]
  [-0.62767833 -0.30741733  0.14819752  0.44313088]
  [ 0.          0.          0.          0.        ]]

 [[-0.99152333 -0.1006391   0.28767768  0.76360202]
  [ 0.          0.          0.          0.        ]
  [ 0.          0.          0.          0.        ]
  [ 0.          0.          0.          0.        ]]]
[[-0.62767833 -0.30741733  0.14819752  0.44313088]
 [-0.99152333 -0.1006391   0.28767768  0.76360202]]

• 对于使用LSTMCell（另一种流行选项）的其他读者来说，情况有所不同。 LSTMCell以不同的方式维护状态 - 单元状态是实际单元状态和隐藏状态的元组或连接版本。 因此，要访问最终的隐藏权重，您可以在单元初始化期间将（ is_state_tuple设置为True ），最终状态将是元组:(最终单元状态，最终隐藏权重）。 那么，在这种情况下，

  _，（_，h）= tf.nn.dynamic_rnn（单元格，输入，长度，initial_state = cell_state）

会给你最后的重量。

参考文献： Tensorflow LSTM中的c_state和m_state https://github.com/tensorflow/tensorflow/blob/438604fc885208ee05f9eef2d0f2c630e1360a83/tensorflow/python/ops/rnn_cell_impl.py#L308 https://github.com/tensorflow/tensorflow/blob/438604fc885208ee05f9eef2d0f2c630e1360a83 /tensorflow/python/ops/rnn_cell_impl.py#L415

Answer 4

实际上，解决方案并不那么难。 我实现了以下代码：

slices = []
for index, l in enumerate(tf.unstack(lengths)):
    slice = tf.slice(rnn_out, begin=[index, l - 1, 0], size=[1, 1, 3])
    slices.append(slice)
last = tf.concat(0, slices)

因此，完整的代码段如下：

import numpy as np
import tensorflow as tf

batch = 2
dim = 3
hidden = 4

lengths = tf.placeholder(dtype=tf.int32, shape=[batch])
inputs = tf.placeholder(dtype=tf.float32, shape=[batch, None, dim])
cell = tf.nn.rnn_cell.GRUCell(hidden)
cell_state = cell.zero_state(batch, tf.float32)
output, _ = tf.nn.dynamic_rnn(cell, inputs, lengths, initial_state=cell_state)

inputs_ = np.asarray([[[0, 0, 0], [1, 1, 1], [2, 2, 2], [3, 3, 3]],
                    [[6, 6, 6], [7, 7, 7], [8, 8, 8], [9, 9, 9]]],
                    dtype=np.int32)
lengths_ = np.asarray([3, 1], dtype=np.int32)

slices = []
for index, l in enumerate(tf.unstack(lengths)):
    slice = tf.slice(output, begin=[index, l - 1, 0], size=[1, 1, 3])
    slices.append(slice)
last = tf.concat(0, slices)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    outputs = sess.run([output, last], {inputs: inputs_, lengths: lengths_})
    print 'RNN output:'
    print(outputs[0])
    print
    print 'last relevant output:'
    print(outputs[1])

并输出：

RNN output:
[[[ 0.          0.          0.          0.        ]
 [-0.06667092 -0.09284072  0.01098599 -0.03676109]
 [-0.09101103 -0.19828682  0.03546784 -0.08721405]
 [ 0.          0.          0.          0.        ]]

[[-0.00025157 -0.05704876  0.05527233 -0.03741353]
 [ 0.          0.          0.          0.        ]
 [ 0.          0.          0.          0.        ]
 [ 0.          0.          0.          0.        ]]]

last relevant output:
[[[-0.09101103 -0.19828682  0.03546784]]

 [[-0.00025157 -0.05704876  0.05527233]]]