自然语言处理（NLP）Bert与Lstm结合
https://blog.csdn.net/zhangtingduo/article/details/1084744013

1.完整过程

可以参考：https://blog.csdn.net/zhangtingduo/article/details/1084744013
这里只重要的步骤

1.1 我们参考文章的模型

import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import TensorDataset, DataLoader

# 利用transformers 先进行分字编码
from transformers import BertTokenizer,BertModel
tokenizer = BertTokenizer.from_pretrained("./chinese-bert_chinese_wwm_pytorch/data")
# result_comments是data的数据集
result_comments_id=tokenizer(result_comments,padding=True,truncation=True,max_length=200,return_tensors='pt')

# 模型
class bert_lstm(nn.Module):
    def __init__(self, hidden_dim,output_size,n_layers,bidirectional=True, drop_prob=0.5):
        super(bert_lstm, self).__init__()
 
        self.output_size = output_size
        self.n_layers = n_layers
        self.hidden_dim = hidden_dim
        self.bidirectional = bidirectional
        
        #Bert ----------------重点，bert模型需要嵌入到自定义模型里面
        self.bert=BertModel.from_pretrained("../chinese-bert_chinese_wwm_pytorch/data")
        for param in self.bert.parameters():
            param.requires_grad = True
        
        # LSTM layers
        self.lstm = nn.LSTM(768, hidden_dim, n_layers, batch_first=True,bidirectional=bidirectional)
        
        # dropout layer
        self.dropout = nn.Dropout(drop_prob)
        
        # linear and sigmoid layers
        if bidirectional:
            self.fc = nn.Linear(hidden_dim*2, output_size)
        else:
            self.fc = nn.Linear(hidden_dim, output_size)
          
        #self.sig = nn.Sigmoid()
 
    def forward(self, x, hidden):
        batch_size = x.size(0)
        #生成bert字向量
        x=self.bert(x)[0]     #bert 字向量
        
        # lstm_out
        #x = x.float()
        lstm_out, (hidden_last,cn_last) = self.lstm(x, hidden)
        #print(lstm_out.shape)   #[32,100,768]
        #print(hidden_last.shape)   #[4, 32, 384]
        #print(cn_last.shape)    #[4, 32, 384]
        
        #修改 双向的需要单独处理
        if self.bidirectional:
            #正向最后一层，最后一个时刻
            hidden_last_L=hidden_last[-2]
            #print(hidden_last_L.shape)  #[32, 384]
            #反向最后一层，最后一个时刻
            hidden_last_R=hidden_last[-1]
            #print(hidden_last_R.shape)   #[32, 384]
            #进行拼接
            hidden_last_out=torch.cat([hidden_last_L,hidden_last_R],dim=-1)
            #print(hidden_last_out.shape,'hidden_last_out')   #[32, 768]
        else:
            hidden_last_out=hidden_last[-1]   #[32, 384]
            
            
        # dropout and fully-connected layer
        out = self.dropout(hidden_last_out)
        #print(out.shape)    #[32,768]
        out = self.fc(out)
        
        return out
    
    def init_hidden(self, batch_size):
        weight = next(self.parameters()).data
        
        number = 1
        if self.bidirectional:
            number = 2
        
        if (USE_CUDA):
            hidden = (weight.new(self.n_layers*number, batch_size, self.hidden_dim).zero_().float().cuda(),
                      weight.new(self.n_layers*number, batch_size, self.hidden_dim).zero_().float().cuda()
                     )
        else:
            hidden = (weight.new(self.n_layers*number, batch_size, self.hidden_dim).zero_().float(),
                      weight.new(self.n_layers*number, batch_size, self.hidden_dim).zero_().float()
                     )
        
        return hidden

1.2 我们自己的