Stateless means there is no memory of the past. Every transaction is performed as if it were being done for the very first time. Stateful means that there is memory of the past. Previous transactions are remembered and may affect the current transaction. Stateless: // The state is derived by what is passed into the … Read more
I found out it was easiest to save the whole state for all layers in a placeholder. init_state = np.zeros((num_layers, 2, batch_size, state_size)) … state_placeholder = tf.placeholder(tf.float32, [num_layers, 2, batch_size, state_size]) Then unpack it and create a tuple of LSTMStateTuples before using the native tensorflow RNN Api. l = tf.unpack(state_placeholder, axis=0) rnn_tuple_state = tuple( [tf.nn.rnn_cell.LSTMStateTuple(l[idx][0], … Read more