RNN(Recurrent Neutral Network,循环神经网络),主要应用于自然语言处理NLP。
因为Pytorch中没有String类型数据,需要引入序列表示法(sequence representation)对文本进行表示。
表示方法:[seq_len:一句话的单词数,feature_len:每个单词的表示方法]
文本信息的表达方式:
import torch import torch.nn as nn word_to_ix = {"hello":0,"world":1} embeds = nn.Embedding(2,5) #2行5列 一共有2个单词,用5位的feature来表示 lookup_tensor = torch.tensor([word_to_ix["hello"]],dtype=torch.long) hello_embed = embeds(lookup_tensor) print(hello_embed) #tensor([[-0.2169, 0.3653, 0.7812, -0.8420, -0.2815]], # grad_fn=<EmbeddingBackward0>) word_to_ix = {"hello":0,"world":1} embeds = nn.Embedding(2,5) #2行5列 一共有2个单词,用5位的feature来表示 lookup_tensor = torch.tensor([word_to_ix["hello"]],dtype=torch.long) hello_embed = embeds(lookup_tensor) print(hello_embed) #tensor([[-0.2169, 0.3653, 0.7812, -0.8420, -0.2815]], # grad_fn=<EmbeddingBackward0>)
from torchnlp.word_to_vector import GloVe vectors = GloVe() vector["hello"]
两种引入方式:[word num, b, word vec] 或者 [b, word num, word vec ] 第一种常用
对每一个单词进行 x@w1+b1 操作,每个单词都有不同的参数
共享参数,用同一个w和b
每一个单词运算表示:x @ wxh +h @ whh
增加了一个h单元,相当于一个memory单元。
RNN的网络为yt = why*ht
ht=激活函数(Whh* ht-1+Wxh *xt) 常用的为tanh
模型的反向传播:BPTT(back propagation through time)
run = nn.RNN(100,10) #word vec 单词的表示位数, memory 记忆节点 run._parameters.keys() #odict_keys(['weight_ih_l0', 'weight_hh_l0', 'bias_ih_l0', 'bias_hh_l0']) run.weight_hh_l0.shape, run.weight_ih_l0.shape #(torch.Size([10, 10]), torch.Size([10, 100])) run.bias_hh_l0.shape, run.bias_ih_l0.shape #(torch.Size([10]), torch.Size([10]))
nn.RNN(input_size:单词的表示方法维度,hidden_size:记忆的维度:,num_layers:默认是1)
前向传播,一步到位 out, ht = forward(x, h0)
x:[一句话单词数,batch几句话,表示的维度]
h0/ht:[层数,batch,记忆(参数)的维度]
out:[一句话单词数,batch,参数的维度]
import torch import torch.nn as nn run = nn.RNN(input_size=100, hidden_size=20, num_layers=1) print(run) #RNN(100, 20) x = torch.randn(10,3,100) h = torch.zeros(1,3,20) out,h1 = run(x,h) print(out.shape,h1.shape) #torch.Size([10, 3, 20]) torch.Size([1, 3, 20])
nn.RNNCell(input_size:单词的表示方法维度,hidden_size:记忆的维度:,num_layers:默认是1)
前向传播:ht=rnncell(xt,ht_1)
xt:[batch,word维度]
ht_1/ht:[层数,batch,参数的维度]
#RNNCell x = torch.randn(10,3,100) cell = nn.RNNCell(100,20) h1 = torch.zeros(3,20) #人为控制一句话的单词数 for xt in x: print(xt) h1 = cell(xt,h1) print(h1.shape) #torch.Size([3, 20])