I read the documentation of tf.dynamic.rnn in https://www.tensorflow.org/api_docs/python/tf/nn/dynamic_rnn
and used it to make a single layer rnn of multiple time-steps. I was wondering if I could use tf.dynamic.rnn to stack multiple hidden layers. Is it possible to do so?
Please look at the following code snippet:
Then pass this cell to
tf.dynamic.rnn
.