其实就是将h层加深

import torch
from torch import nn
from d2l import torch as d2l


batch_size, num_steps = 32, 35
train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)

vocab_size, num_hiddens, num_layers = len(vocab), 256, 2
num_inputs = vocab_size
device = d2l.try_gpu()
lstm_layer = nn.LSTM(num_inputs, num_hiddens, num_layers)
model = d2l.RNNModel(lstm_layer, vocab_size)
model = model.to(device)

num_epochs, lr = 1000, 2
d2l.train_ch8(model, train_iter, vocab, lr, num_epochs, device)
d2l.plt.show()

perplexity 1.0, 253085.8 tokens/sec on cuda:0
time traveller for so it will be convenient to speak of himwas e
traveller with a slight accession ofcheerfulness really thi