Question

with tf.variable_scope('forward'):
  cell_img_fwd = tf.nn.rnn_cell.GRUCell(hidden_state_size, hidden_state_size)
  img_init_state_fwd = rnn_img_mapped[:, 0, :]
  img_init_state_fwd = tf.multiply(
      img_init_state_fwd, 
      tf.zeros([batch_size, hidden_state_size]))
  rnn_outputs2, final_state2 = tf.nn.dynamic_rnn(
      cell_img_fwd, 
      rnn_img_mapped, 
      initial_state=img_init_state_fwd, 
      dtype=tf.float32)

这是我用于输入尺寸100x196x50的GRU的代码，它应该沿第二维（即196）解压缩。 hidden_state_size为50，batch_size为100.但是我收到以下错误：

ValueError: The two structures don't have the same number of elements.
First structure: Tensor("backward/Tile:0", shape=(100, 50), dtype=float32), 
second structure: 
  (<tf.Tensor 'backward/bwd_states/while/GRUCell/add:0' shape=(100, 50) dtype=float32>, 
   <tf.Tensor 'backward/bwd_states/while/GRUCell/add:0' shape=(100, 50) dtype=float32>).

有任何线索如何解决这个问题？

Answer 1

你好我遇到了同样的问题，我试着这样做：

highest = tf.map_fn(lambda x : (-x, x), indices)

这给了我一个类似的错误信息：

ValueError: The two structures don't have the same number of elements.

First structure (1 elements): <dtype: 'int32'>

Second structure (2 elements): (<tf.Tensor 'map/while/Neg:0' shape=() dtype=int32>, <tf.Tensor 'map/while/TensorArrayReadV3:0' shape=() dtype=int32>)

我通过明确表示dtypes来解决这个问题：

highest = tf.map_fn(lambda x : (-x, x), indices, dtype=(tf.int32, tf.int32))

ValueError：这两个结构没有相同数量的元素

1 个答案: