def get_initial_state(self, inputs):
  # build an all-zero tensor of shape (samples, output_dim)
  initial_state = K.zeros_like(inputs)  # (samples, timesteps, input_dim)
  initial_state = K.sum(initial_state, axis=(1, 2))  # (samples,)
  initial_state = K.expand_dims(initial_state)  # (samples, 1)