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。
