.. _sec_rnn-concise:
循环神经网络的简洁实现
======================
虽然 :numref:`sec_rnn_scratch`
对了解循环神经网络的实现方式具有指导意义，但并不方便。
本节将展示如何使用深度学习框架的高级API提供的函数更有效地实现相同的语言模型。
我们仍然从读取时光机器数据集开始。
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
import mindspore
import mindspore.nn as nn
import mindspore.ops as ops
import numpy as np
from d2l import mindspore as d2l
batch_size, num_steps = 32, 35
train_iter, vocab = d2l.load_data_time_machine(batch_size, num_steps)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
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)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
num_hiddens = 256
rnn_layer = nn.RNN(len(vocab), num_hiddens)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
num_hiddens = 256
rnn_layer = nn.RNN(len(vocab), num_hiddens)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
state = ops.zeros((1, batch_size, num_hiddens))
state.shape
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
(1, 32, 256)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
state = torch.zeros((1, batch_size, num_hiddens))
state.shape
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
torch.Size([1, 32, 256])
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
X = ops.rand(num_steps, batch_size, len(vocab))
Y, state_new = rnn_layer(X, state)
Y.shape, state_new.shape
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
((35, 32, 256), (1, 32, 256))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
X = torch.rand(size=(num_steps, batch_size, len(vocab)))
Y, state_new = rnn_layer(X, state)
Y.shape, state_new.shape
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
(torch.Size([35, 32, 256]), torch.Size([1, 32, 256]))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
class RNNModel(nn.Cell):
"""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.Dense(self.num_hiddens, self.vocab_size)
else:
self.num_directions = 2
self.linear = nn.Dense(self.num_hiddens * 2, self.vocab_size)
def construct(self, inputs, state):
X = ops.one_hot(inputs.T, self.vocab_size, mindspore.tensor(1.0), mindspore.tensor(0.0))
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, batch_size=1):
if not isinstance(self.rnn, nn.LSTM):
# nn.GRU以张量作为隐状态
return ops.zeros((self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens))
else:
# nn.LSTM以元组作为隐状态
return (ops.zeros((
self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens)),
ops.zeros((
self.num_directions * self.rnn.num_layers,
batch_size, self.num_hiddens)))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@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))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
net = RNNModel(rnn_layer, vocab_size=len(vocab))
d2l.predict_ch8('time traveller', 10, net, vocab)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'time travellerhnhnhnhnhn'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
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)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'time travellereeeeeeeeee'
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
num_epochs, lr = 500, 1
d2l.train_ch8(net, train_iter, vocab, lr, num_epochs)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
困惑度 1.3, 93485.7 词元/秒
time traveller held in his hand was a glitteringmetallic framewa
traveller aron the parme weshile seant oon and there is are
.. figure:: output_rnn-concise_eff2f4_57_1.png
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
num_epochs, lr = 500, 1
d2l.train_ch8(net, train_iter, vocab, lr, num_epochs, device)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
perplexity 1.3, 1366332.1 tokens/sec on cuda:0
time traveller after the pauserequired for the proper assimilati
travellerther cover to mpass outhe thavereastouth than bags
.. figure:: output_rnn-concise_eff2f4_60_1.svg
.. raw:: html
.. raw:: html
.. raw:: html
`讨论 `__
.. raw:: html
.. raw:: html
`讨论 `__
.. raw:: html
.. raw:: html