【nlp入门实战】Pytorch文本分类入门

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍖 原作者：K同学啊

文本分类流程图

数据初始化

import torch
import torch.nn as nn
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings
from torchtext.datasets import AG_NEWS
from torchtext.vocab import build_vocab_from_iterator
import torchtext.data.utils as utils
from torch.utils.data import DataLoader
from torch import nn
import time
 
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

train_iter = AG_NEWS(split='train')

tokenizer = utils.get_tokenizer('basic_english')
 
def yield_tokens(data_iter):
    for _, text in data_iter:
        yield tokenizer(text)
 
vocab = build_vocab_from_iterator(yield_tokens(train_iter),specials=["<unk>"])
vocab.set_default_index(vocab["<unk>"])  #设置默认索引，如果找不到单词，则会选择默认索引
 
print(vocab(['here', 'is', 'an', 'example']))
 
text_pipeline = lambda  x: vocab(tokenizer(x))
label_pipeline = lambda x: int(x) - 1
 
print(text_pipeline('here is an example'))
print(label_pipeline('10'))

[475, 21, 30, 5297]
[475, 21, 30, 5297]
9

def collate_batch(batch):
    label_list, text_list, offsets = [], [], [0]

    for (_label, _text) in batch:
        label_list.append(label_pipeline(_label))
        process_text = torch.tensor(text_pipeline(_text), dtype=torch.int64)
        text_list.append(process_text)

        offsets.append(process_text.size(0))

    label_list = torch.tensor(label_list, dtype=torch.int64)
    text_list = torch.cat(text_list)
    offsets = torch.tensor(offsets[:-1]).cumsum(dim=0)

    return label_list.to(device), text_list.to(device), offsets.to(device)


dataloader = DataLoader(train_iter, batch_size=8,
                        shuffle=False, collate_fn=collate_batch)

创建模型

class TextClassificationModel(nn.Module):
    def __init__(self, vocab_size, embed_dim, num_class):
        super(TextClassificationModel, self).__init__()
        self.embedding = nn.EmbeddingBag(vocab_size, embed_dim, sparse=False)
        self.fc = nn.Linear(embed_dim, num_class)
        self.init_weights()

    def init_weights(self):
        initrange = 0.5
        self.embedding.weight.data.uniform_(-initrange, initrange)
        self.fc.weight.data.uniform_(-initrange, initrange)

    def forward(self, text, offsets):
        embedded = self.embedding(text, offsets)
        return self.fc(embedded)

num_class = len(set([label for (label, text) in train_iter]))
vocab_size = len(vocab)
em_size = 64
model = TextClassificationModel(vocab_size, em_size, num_class).to(device)

import time


def train(dataloader):
    model.train()  # 切换为训练模式
    total_acc, train_loss, total_count = 0, 0, 0
    log_interval = 500
    start_time = time.time()

    for idx, (label, text, offsets) in enumerate(dataloader):

        predicted_label = model(text, offsets)

        optimizer.zero_grad()                    # grad属性归零
        loss = criterion(predicted_label, label)  # 计算网络输出和真实值之间的差距，label为真实值
        loss.backward()                          # 反向传播
        optimizer.step()  # 每一步自动更新

        # 记录acc与loss
        total_acc += (predicted_label.argmax(1) == label).sum().item()
        train_loss += loss.item()
        total_count += label.size(0)

        if idx % log_interval == 0 and idx > 0:
            elapsed = time.time() - start_time
            print('| epoch {:1d} | {:4d}/{:4d} batches '
                  '| train_acc {:4.3f} train_loss {:4.5f}'.format(epoch, idx, len(dataloader),
                                                                  total_acc/total_count, train_loss/total_count))
            total_acc, train_loss, total_count = 0, 0, 0
            start_time = time.time()


def evaluate(dataloader):
    model.eval()  # 切换为测试模式
    total_acc, train_loss, total_count = 0, 0, 0

    with torch.no_grad():
        for idx, (label, text, offsets) in enumerate(dataloader):
            predicted_label = model(text, offsets)

            loss = criterion(predicted_label, label)  # 计算loss值
            # 记录测试数据
            total_acc += (predicted_label.argmax(1) == label).sum().item()
            train_loss += loss.item()
            total_count += label.size(0)

    return total_acc/total_count, train_loss/total_count

模型训练

from torch.utils.data.dataset import random_split
from torchtext.data.functional import to_map_style_dataset
# 超参数
EPOCHS = 10  # epoch
LR = 5  # 学习率
BATCH_SIZE = 64  # batch size for training

criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=LR)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.1)
total_accu = None

train_iter, test_iter = AG_NEWS()  # 加载数据
train_dataset = to_map_style_dataset(train_iter)
test_dataset = to_map_style_dataset(test_iter)
num_train = int(len(train_dataset) * 0.95)

split_train_, split_valid_ = random_split(train_dataset,
                                          [num_train, len(train_dataset)-num_train])

train_dataloader = DataLoader(split_train_, batch_size=BATCH_SIZE,
                              shuffle=True, collate_fn=collate_batch)
valid_dataloader = DataLoader(split_valid_, batch_size=BATCH_SIZE,
                              shuffle=True, collate_fn=collate_batch)
test_dataloader = DataLoader(test_dataset, batch_size=BATCH_SIZE,
                             shuffle=True, collate_fn=collate_batch)

for epoch in range(1, EPOCHS + 1):
    epoch_start_time = time.time()
    train(train_dataloader)
    val_acc, val_loss = evaluate(valid_dataloader)

    if total_accu is not None and total_accu > val_acc:
        scheduler.step()
    else:
        total_accu = val_acc
    print('-' * 69)
    print('| epoch {:1d} | time: {:4.2f}s | '
          'valid_acc {:4.3f} valid_loss {:4.3f}'.format(epoch,
                                                        time.time() - epoch_start_time,
                                                        val_acc, val_loss))

    print('-' * 69)

| epoch 1 |  500/1782 batches | train_acc 0.716 train_loss 0.01123
| epoch 1 | 1000/1782 batches | train_acc 0.862 train_loss 0.00631
| epoch 1 | 1500/1782 batches | train_acc 0.884 train_loss 0.00539
---------------------------------------------------------------------
| epoch 1 | time: 24.46s | valid_acc 0.801 valid_loss 0.009
---------------------------------------------------------------------
| epoch 2 |  500/1782 batches | train_acc 0.906 train_loss 0.00447
| epoch 2 | 1000/1782 batches | train_acc 0.908 train_loss 0.00430
| epoch 2 | 1500/1782 batches | train_acc 0.904 train_loss 0.00448
---------------------------------------------------------------------
| epoch 2 | time: 30.74s | valid_acc 0.903 valid_loss 0.005
---------------------------------------------------------------------
| epoch 3 |  500/1782 batches | train_acc 0.920 train_loss 0.00376
| epoch 3 | 1000/1782 batches | train_acc 0.919 train_loss 0.00381
| epoch 3 | 1500/1782 batches | train_acc 0.917 train_loss 0.00390
---------------------------------------------------------------------
| epoch 3 | time: 31.00s | valid_acc 0.881 valid_loss 0.005
---------------------------------------------------------------------
| epoch 4 |  500/1782 batches | train_acc 0.936 train_loss 0.00306
| epoch 4 | 1000/1782 batches | train_acc 0.938 train_loss 0.00299
| epoch 4 | 1500/1782 batches | train_acc 0.939 train_loss 0.00298
---------------------------------------------------------------------
| epoch 4 | time: 23.12s | valid_acc 0.911 valid_loss 0.004
---------------------------------------------------------------------
| epoch 5 |  500/1782 batches | train_acc 0.940 train_loss 0.00290
| epoch 5 | 1000/1782 batches | train_acc 0.941 train_loss 0.00286
| epoch 5 | 1500/1782 batches | train_acc 0.940 train_loss 0.00294
---------------------------------------------------------------------
| epoch 5 | time: 23.07s | valid_acc 0.910 valid_loss 0.004
---------------------------------------------------------------------
| epoch 6 |  500/1782 batches | train_acc 0.941 train_loss 0.00286
| epoch 6 | 1000/1782 batches | train_acc 0.942 train_loss 0.00283
| epoch 6 | 1500/1782 batches | train_acc 0.942 train_loss 0.00282
---------------------------------------------------------------------
| epoch 6 | time: 23.04s | valid_acc 0.911 valid_loss 0.004
---------------------------------------------------------------------
| epoch 7 |  500/1782 batches | train_acc 0.941 train_loss 0.00283
| epoch 7 | 1000/1782 batches | train_acc 0.941 train_loss 0.00285
| epoch 7 | 1500/1782 batches | train_acc 0.945 train_loss 0.00279
---------------------------------------------------------------------
| epoch 7 | time: 23.00s | valid_acc 0.911 valid_loss 0.004
---------------------------------------------------------------------
| epoch 8 |  500/1782 batches | train_acc 0.943 train_loss 0.00279
| epoch 8 | 1000/1782 batches | train_acc 0.941 train_loss 0.00289
| epoch 8 | 1500/1782 batches | train_acc 0.944 train_loss 0.00271
---------------------------------------------------------------------
| epoch 8 | time: 22.80s | valid_acc 0.911 valid_loss 0.004
---------------------------------------------------------------------
| epoch 9 |  500/1782 batches | train_acc 0.943 train_loss 0.00278
| epoch 9 | 1000/1782 batches | train_acc 0.943 train_loss 0.00280
| epoch 9 | 1500/1782 batches | train_acc 0.943 train_loss 0.00279
---------------------------------------------------------------------
| epoch 9 | time: 30.13s | valid_acc 0.911 valid_loss 0.004
---------------------------------------------------------------------
| epoch 10 |  500/1782 batches | train_acc 0.943 train_loss 0.00278
| epoch 10 | 1000/1782 batches | train_acc 0.944 train_loss 0.00278
| epoch 10 | 1500/1782 batches | train_acc 0.942 train_loss 0.00281
---------------------------------------------------------------------
| epoch 10 | time: 23.07s | valid_acc 0.911 valid_loss 0.004
---------------------------------------------------------------------

print('Checking the results of test dataset.')
test_acc, test_loss = evaluate(test_dataloader)
print('test accuracy {:8.3f}'.format(test_acc))

Checking the results of test dataset.
test accuracy 0.908