《动手学深度学习(PyTorch版)》笔记8.6

注:书中对代码的讲解并不详细,本文对很多细节做了详细注释。另外,书上的源代码是在Jupyter Notebook上运行的,较为分散,本文将代码集中起来,并加以完善,全部用vscode在python 3.9.18下测试通过,同时对于书上部分章节也做了整合。

Chapter8 Recurrent Neural Networks

8.6 Concise Implementation of RNN

import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l
import matplotlib.pyplot as plt

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

num_hiddens = 256
rnn_layer = nn.RNN(len(vocab), num_hiddens)

state = torch.zeros((1, batch_size, num_hiddens))
print(state.shape)

X = torch.rand(size=(num_steps, batch_size, len(vocab)))
Y, state_new = rnn_layer(X, state)#Y不涉及输出层的计算
print(Y.shape, state_new.shape)

class RNNModel(nn.Module):#@save
    """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
            #GRU为门控循环单元(Gated Recurrent Unit),是一种流行的循环神经网络变体。
            #GRU使用了一组门控机制来控制信息的流动,包括更新门(update gate)和重置门(reset gate),以更好地捕捉长期依赖关系
            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
            #LSTM代表长短期记忆网络(Long Short-Term Memory),是另一种常用的循环神经网络类型。
            #相比于简单的循环神经网络,LSTM引入了三个门控单元:输入门(input gate)、遗忘门(forget gate)和输出门(output gate),以及一个记忆单元(cell state),可以更有效地处理长期依赖性。
            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))
            
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)

num_epochs, lr = 500, 1
d2l.train_ch8(net, train_iter, vocab, lr, num_epochs, device)
plt.show()

训练结果:
《动手学深度学习(PyTorch版)》笔记8.6_第1张图片

与上一节相比,由于pytorch的高级API对代码进行了更多的优化,该模型在较短的时间内达到了较低的困惑度。

你可能感兴趣的:(python,深度学习笔记,深度学习,pytorch,笔记,算法,人工智能,python)