import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l
batch_size, num_steps = 32, 35
train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)
一样的加载 train_iter,vocab
num_hiddens = 256
rnn_layer = nn.RNN(len(vocab), num_hiddens)
使用nn提供的RNN,只需要传入两个参数(len(vocab), num_hiddens)
state = torch.zeros((1, batch_size, num_hiddens))
state.shape
隐藏状态还是要自己初始化,上一节说过,我们将state存在一个turple里(铺垫之后的LSTM),这里多了一个参数 1,
torch.Size([1, 32, 256])
测试一下
X = torch.rand(size=(num_steps, batch_size, len(vocab)))
Y, state_new = rnn_layer(X, state)
Y.shape, state_new.shape
输出
(torch.Size([35, 32, 256]), torch.Size([1, 32, 256]))
这里注意,torch的RNN和我们上一届自己写的有两个区别:
- 这里的Y并不是最终输出的Y,而是最后Linear层之前的Y,最后一个维度是256,不是28,需要我们自己再写一个线性层
- 这个Y并没有进行拼接成 [35 * 32,256]
#@save
class RNNModel(nn.Module):
"""循环神经网络模型"""
def __init__(self, rnn_layer, vocab_size, **kwargs):
super(RNNModel, self).__init__(**kwargs)
self.rnn = rnn_layer
self.vocab_size = vocab_size
self.num_hiddens = self.rnn.hidden_size
# 如果RNN是双向的(之后将介绍),num_directions应该是2,否则应该是1
if not self.rnn.bidirectional:
self.num_directions = 1
self.linear = nn.Linear(self.num_hiddens, self.vocab_size)
else:
self.num_directions = 2
self.linear = nn.Linear(self.num_hiddens * 2, self.vocab_size)
def forward(self, inputs, state):
X = F.one_hot(inputs.T.long(), self.vocab_size)
X = X.to(torch.float32)
Y, state = self.rnn(X, state)
# 全连接层首先将Y的形状改为(时间步数*批量大小,隐藏单元数)
# 它的输出形状是(时间步数*批量大小,词表大小)。
output = self.linear(Y.reshape((-1, Y.shape[-1])))
return output, state
def begin_state(self, device, batch_size=1):
if not isinstance(self.rnn, nn.LSTM):
# nn.GRU以张量作为隐状态
return torch.zeros((self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens),
device=device)
else:
# nn.LSTM以元组作为隐状态
return (torch.zeros((
self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens), device=device),
torch.zeros((
self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens), device=device))
self.linear = nn.Linear(self.num_hiddens, self.vocab_size)
就像我们刚才说的,这里需要自己定义输出的线性层
预测是一样的,看看
device = d2l.try_gpu()
net = RNNModel(rnn_layer, vocab_size=len(vocab))
net = net.to(device)
d2l.predict_ch8('time traveller', 10, net, vocab, device)
输出
'time travellermmjmrmmj'
训练
num_epochs, lr = 500, 1
d2l.train_ch8(net, train_iter, vocab, lr, num_epochs, device)
perplexity 1.3, 176156.1 tokens/sec on cuda:0
time travellerit s against reason said filby but you willnever c
travelleryou can show al and down can of sit ee ascond dfar