0

I run the sample code recurrent_network.py.

I wish print all the x, it's a placehoder. In the function: RNN(x, weights, biases):

What can I do?

Key point:

    x = tf.transpose(x, [1, 0, 2])
    # Reshaping to (n_steps*batch_size, n_input)
    x = tf.reshape(x, [-1, n_input])
    # Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
    x = tf.split(0, n_steps, x)
chrki
  • 6,143
  • 6
  • 35
  • 55
Shengjun JI
  • 1
  • 2

1 Answers1

0

Please see this post for details. I usually use tf.Print() myself.

Community
  • 1
  • 1
David Wong
  • 748
  • 3
  • 6