What is memory efficient transduction in dynet explain with example

Recipe Objective - What is memory efficient transduction explain with example?

In this method first, we will create the RNN model. Then we will use the "add_inputs(xs)" method, where "xs" is a list of expressions and then we will see the sequence of output expressions.

import dynet as dy



Creating RNN model.

pc = dy.ParameterCollection()
num_layers=3
input_dim=60
hidden_dim=20
RNNbuilder = dy.SimpleRNNBuilder(num_layers, input_dim, hidden_dim, pc)

x1 = dy.vecInput(input_dim)

rnn_state = RNNbuilder.initial_state()
xs = [x1,x1,x1]
states = rnn_state.add_inputs(xs)
outputs = [s.output() for s in states]
hs = [s.h() for s in states]
print(outputs, hs)