pytorch 如何使用batch训练lstm网络

batch的lstm

# 导入相应的包
import torch
import torch.nn as nn
import torch.nn.functional as f
import torch.optim as optim
import torch.utils.data as data 
torch.manual_seed(1) 
 
# 准备数据的阶段
def prepare_sequence(seq, to_ix):
    idxs = [to_ix[w] for w in seq]
    return torch.tensor(idxs, dtype=torch.long)
  
with open("/home/lstm_train.txt", encoding='utf8') as f:
    train_data = []
    word = []
    label = []
    data = f.readline().strip()
    while data:
        data = data.strip()
        sp = data.split(' ')
        if len(sp) == 2:
            word.append(sp[0])
            label.append(sp[1])
        else:
            if len(word) == 100 and 'i-pro' in label:
                train_data.append((word, label))
            word = []
            label = []
        data = f.readline()
 
word_to_ix = {}
for sent, _ in train_data:
    for word in sent:
        if word not in word_to_ix:
            word_to_ix[word] = len(word_to_ix)
 
tag_to_ix = {"o": 0, "i-pro": 1}
for i in range(len(train_data)):
    train_data[i] = ([word_to_ix[t] for t in train_data[i][0]], [tag_to_ix[t] for t in train_data[i][1]])
 
# 词向量的维度
embedding_dim = 128
 
# 隐藏层的单元数
hidden_dim = 128
 
# 批大小
batch_size = 10  
class lstmtagger(nn.module):
 
    def __init__(self, embedding_dim, hidden_dim, vocab_size, tagset_size, batch_size):
        super(lstmtagger, self).__init__()
        self.hidden_dim = hidden_dim
        self.batch_size = batch_size
        self.word_embeddings = nn.embedding(vocab_size, embedding_dim)
 
        # the lstm takes word embeddings as inputs, and outputs hidden states
        # with dimensionality hidden_dim.
        self.lstm = nn.lstm(embedding_dim, hidden_dim, batch_first=true)
 
        # the linear layer that maps from hidden state space to tag space
        self.hidden2tag = nn.linear(hidden_dim, tagset_size)
 
    def forward(self, sentence):
        embeds = self.word_embeddings(sentence)
        # input_tensor = embeds.view(self.batch_size, len(sentence) // self.batch_size, -1)
        lstm_out, _ = self.lstm(embeds)
        tag_space = self.hidden2tag(lstm_out)
        scores = f.log_softmax(tag_space, dim=2)
        return scores
 
    def predict(self, sentence):
        embeds = self.word_embeddings(sentence)
        lstm_out, _ = self.lstm(embeds)
        tag_space = self.hidden2tag(lstm_out)
        scores = f.log_softmax(tag_space, dim=2)
        return scores 
 
loss_function = nn.nllloss()
model = lstmtagger(embedding_dim, hidden_dim, len(word_to_ix), len(tag_to_ix), batch_size)
optimizer = optim.sgd(model.parameters(), lr=0.1)
 
data_set_word = []
data_set_label = []
for data_tuple in train_data:
    data_set_word.append(data_tuple[0])
    data_set_label.append(data_tuple[1])
torch_dataset = data.tensordataset(torch.tensor(data_set_word, dtype=torch.long), torch.tensor(data_set_label, dtype=torch.long))
# 把 dataset 放入 dataloader
loader = data.dataloader(
    dataset=torch_dataset,  # torch tensordataset format
    batch_size=batch_size,  # mini batch size
    shuffle=true,  #
    num_workers=2,  # 多线程来读数据
)
 
# 训练过程
for epoch in range(200):
    for step, (batch_x, batch_y) in enumerate(loader):
        # 梯度清零
        model.zero_grad()
        tag_scores = model(batch_x)
 
        # 计算损失
        tag_scores = tag_scores.view(-1, tag_scores.shape[2])
        batch_y = batch_y.view(batch_y.shape[0]*batch_y.shape[1])
        loss = loss_function(tag_scores, batch_y)
        print(loss)
        # 后向传播
        loss.backward()
 
        # 更新参数
        optimizer.step()
 
# 测试过程
with torch.no_grad():
    inputs = torch.tensor([data_set_word[0]], dtype=torch.long)
    print(inputs)
    tag_scores = model.predict(inputs)
    print(tag_scores.shape)
    print(torch.argmax(tag_scores, dim=2))

补充：pytorch基础-使用lstm神经网络实现手写数据集识别

看代码吧~

import numpy as np
import torch
from torch import nn,optim
from torch.autograd import variable
from torchvision import datasets,transforms
from torch.utils.data import dataloader

# 训练集
train_data = datasets.mnist(root="./", # 存放位置
                            train = true, # 载入训练集
                            transform=transforms.totensor(), # 把数据变成tensor类型
                            download = true # 下载
                           )
# 测试集
test_data = datasets.mnist(root="./",
                            train = false,
                            transform=transforms.totensor(),
                            download = true
                           )

# 批次大小
batch_size = 64
# 装载训练集
train_loader = dataloader(dataset=train_data,batch_size=batch_size,shuffle=true)
# 装载测试集
test_loader = dataloader(dataset=test_data,batch_size=batch_size,shuffle=true)

for i,data in enumerate(train_loader):
    inputs,labels = data
    print(inputs.shape)
    print(labels.shape)
    break

# 定义网络结构
class lstm(nn.module):
    def __init__(self):
        super(lstm,self).__init__()# 初始化
        self.lstm = torch.nn.lstm(
            input_size = 28, # 表示输入特征的大小
            hidden_size = 64, # 表示lstm模块的数量
            num_layers = 1, # 表示lstm隐藏层的层数
            batch_first = true # lstm默认格式input（seq_len,batch,feature）等于true表示input和output变成（batch，seq_len，feature）
        )
        self.out = torch.nn.linear(in_features=64,out_features=10)
        self.softmax = torch.nn.softmax(dim=1)
    def forward(self,x):
        # (batch,seq_len,feature)
        x = x.view(-1,28,28)
        # output:(batch,seq_len,hidden_size)包含每个序列的输出结果
        # 虽然lstm的batch_first为true，但是h_n,c_n的第0个维度还是num_layers
        # h_n :[num_layers,batch,hidden_size]只包含最后一个序列的输出结果
        # c_n:[num_layers,batch,hidden_size]只包含最后一个序列的输出结果
        output,(h_n,c_n) = self.lstm(x)
        output_in_last_timestep = h_n[-1,:,:]
        x = self.out(output_in_last_timestep)
        x = self.softmax(x)
        return x

# 定义模型
model = lstm()
# 定义代价函数
mse_loss = nn.crossentropyloss()# 交叉熵
# 定义优化器
optimizer = optim.adam(model.parameters(),lr=0.001)# 随机梯度下降

# 定义模型训练和测试的方法
def train():
    # 模型的训练状态
    model.train()
    for i,data in enumerate(train_loader):
        # 获得一个批次的数据和标签
        inputs,labels = data
        # 获得模型预测结果（64，10)
        out = model(inputs)
        # 交叉熵代价函数out（batch，c：类别的数量），labels（batch）
        loss = mse_loss(out,labels)
        # 梯度清零
        optimizer.zero_grad()
        # 计算梯度
        loss.backward()
        # 修改权值
        optimizer.step()
        
def test():
    # 模型的测试状态
    model.eval()
    correct = 0 # 测试集准确率
    for i,data in enumerate(test_loader):
        # 获得一个批次的数据和标签
        inputs,labels = data
        # 获得模型预测结果（64，10)
        out = model(inputs)
        # 获得最大值，以及最大值所在的位置
        _,predicted = torch.max(out,1)
        # 预测正确的数量
        correct += (predicted==labels).sum()
    print("test acc:{0}".format(correct.item()/len(test_data)))
    
    correct = 0
    for i,data in enumerate(train_loader): # 训练集准确率
        # 获得一个批次的数据和标签
        inputs,labels = data
        # 获得模型预测结果（64，10)
        out = model(inputs)
        # 获得最大值，以及最大值所在的位置
        _,predicted = torch.max(out,1)
        # 预测正确的数量
        correct += (predicted==labels).sum()
    print("train acc:{0}".format(correct.item()/len(train_data)))

# 训练
for epoch in range(10):
    print("epoch:",epoch)
    train()
    test()

以上为个人经验，希望能给大家一个参考，也希望大家多多支持。