Tensorflow RNN How To Create Zero State With Various Batch Size?

In this question How do I set TensorFlow RNN state when state_is_tuple=True?: the accepted answer initialize the initial state like this: state_placeholder = tf.placeholder(tf.floa

Solution 1:

cell.zero_state accepts a scalar tensor.

Get the batch size of the place holder via tf.shape, then it is done: B = tf.shape(state_placeholder)[0] # the batch size scalar tensor initial_state = cell.zero_state(B)