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

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, :]
  i         


        

Answer 1

Hello I had the same problem, I tried to do this:

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

This gave me a similar error message:

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>)

I resolved this by making the dtypes explicit:

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