Feeding same _initial_state_ to all layers

[vsuarezpaniagua]

In the training phase the self.initial_state is used as cell.zero_state and last_state of the last layer is kept:

self.initial_state = cell.zero_state(args.batch_size, tf.float32)
outputs, last_state = legacy_seq2seq.rnn_decoder(inputs, self.initial_state, cell, loop_function=loop if not training else None, scope='rnnlm')
self.final_state = last_state

However, in the testing phase (def sample()) it seems that all the layers are fed just with the state of the last layer of the previous step, self.final_state, as:

feed = {self.input_data: x, self.initial_state: state}
[probs, state] = sess.run([self.probs, self.final_state], feed)

If I'm not wrong I think all the states of each layer must be kept and then fed them in their corresponding layer for the following steps, not feeding the last one to all the layers.