在TensorFlow折叠中实现TreeLSTM的N-aryTreeLSTM版本

Question

我正在尝试使用TensorFlow Fold实现本文TreeLSTM.实际上,在Tensorflow Fold中,已经有一个TreeLSTM的例子,但是在BinaryTreeLSTM版本中,这是教程:https://github.com/tensorflow/fold/blob/master/tensorflow_fold/g3doc/sentiment.ipynb

我现在要做的是实现一个真正的NaryTreeLSTM,意味着LSTM节点可以是任意数量子节点的父节点,而不仅仅是上面教程中的2节点.

这是我尝试折叠树的尝试,这是上例中的修改版本logits_and_state()"

 def logits_and_state():
  """Creates a block that goes from tokens to (logits, state) tuples."""
  word2vec = (td.GetItem(0) >> td.InputTransform(lookup_word) >>
              td.Scalar('int32') >> word_embedding)

  children_num = 
  children2vec_list = list()
  children2vec_list.append(embed_subtree())
  for i in range(children_num):
    children2vec_list.append(embed_subtree())

  children2vec = tuple(children2vec_list)

  # Trees are binary, so the tree layer takes two states as its input_state.

  zero_state = td.Zeros((tree_lstm.state_size,) * 2)
  # Input is a word vector.
  zero_inp = td.Zeros(word_embedding.output_type.shape[0])

  # word_case = 
  word_case = td.AllOf(word2vec, zero_state)
  children_case = td.AllOf(zero_inp, children2vec)

  tree2vec = td.OneOf(lambda x: 1 if len(x) == 1 else 2), [(1,word_case),(2,children_case)])
  return tree2vec >> tree_lstm >> (output_layer, td.Identity())

这children_num是我现在正在努力的事情,我不知道这个数字,我知道可以通过td.GetItem(1)==> 获得子项的长度将生成一个包含子数组的块== >如何获得该块的实际数量？

您可能会说我应该尝试使用PyTorch或其他一些也提供Dynamic Computation Graph的DL框架,但在我的情况下,要求是严格的Tensorflow Fold.