【动手学深度学习pytorch】学习笔记 9.3. 深度循环神经网络

9.3. 深度循环神经网络 — 动手学深度学习 2.0.0-beta0 documentation (d2l.ai)

rnn.LSTM(num_hiddens, num_layers) 

通过num_layers的值来设定隐藏层数

解释了前面的问题：【动手学深度学习pytorch】学习笔记 8.6. 循环神经网络的简洁实现 - HBU_DAVID - 博客园 (cnblogs.com)

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, len(vocab))
model = model.to(device)

num_epochs, lr = 500, 2
d2l.train_ch8(model, train_iter, vocab, lr, num_epochs, device)

标签：vocab,layers,pytorch,num,d2l,深度,model,size,9.3
来源： https://www.cnblogs.com/hbuwyg/p/16367614.html