Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: RNN that generates Game of Thrones text.
cell = tf.contrib.rnn.MultiRNNCell([drop_cell] * num_layers)
with:
cell = tf.contrib.rnn.MultiRNNCell([create_cell() for _ in range(num_layers)])
otherwise you'll be using the same weights for each LSTM layer and your model is less expressive.
cell = tf.contrib.rnn.MultiRNNCell([drop_cell] * num_layers)
with:
cell = tf.contrib.rnn.MultiRNNCell([create_cell() for _ in range(num_layers)])
otherwise you'll be using the same weights for each LSTM layer and your model is less expressive.