pytorch+文本分类

在PyTorch中进行文本分类，可以使用torchtext库来处理文本数据。下面是一个简单的例子，展示了如何使用torchtext来加载IMDB电影评论数据集，并使用卷积神经网络（CNN）进行情感分类。

首先，需要安装torchtext库：

pip install torchtext

然后，可以使用以下代码来加载IMDB数据集，并将其分为训练集和测试集：

import torch
from torchtext import datasets
from torchtext.data import Field, LabelField, BucketIterator

SEED = 1234

torch.manual_seed(SEED)
torch.backends.cudnn.deterministic = True

TEXT = Field(tokenize='spacy', tokenizer_language='en_core_web_sm')
LABEL = LabelField(dtype=torch.float)

train_data, test_data = datasets.IMDB.splits(TEXT, LABEL)

train_data, valid_data = train_data.split(random_state=random.seed(SEED))

接下来，可以使用预训练的词向量来初始化单词嵌入。这里使用GloVe词向量：

MAX_VOCAB_SIZE = 25_000

TEXT.build_vocab(train_data,
                 max_size=MAX_VOCAB_SIZE,
                 vectors="glove.6B.100d",
                 unk_init=torch.Tensor.normal_)

LABEL.build_vocab(train_data)

然后，可以定义一个CNN模型：

import torch.nn as nn
import torch.nn.functional as F

class CNN(nn.Module):
    def __init__(self, vocab_size, embedding_dim, n_filters, filter_sizes, output_dim, dropout):
        super().__init__()

        self.embedding = nn.Embedding(vocab_size, embedding_dim)

        self.convs = nn.ModuleList([
            nn.Conv2d(in_channels=1,
                      out_channels=n_filters,
                      kernel_size=(fs, embedding_dim))
            for fs in filter_sizes
        ])

        self.fc = nn.Linear(len(filter_sizes) * n_filters, output_dim)

        self.dropout = nn.Dropout(dropout)

    def forward(self, text):
        # text = [sent len, batch size]

        text = text.permute(1, 0)

        # text = [batch size, sent len]

        embedded = self.embedding(text)

        # embedded = [batch size, sent len, emb dim]

        embedded = embedded.unsqueeze(1)

        # embedded = [batch size, 1, sent len, emb dim]

        conved = [F.relu(conv(embedded)).squeeze(3) for conv in self.convs]

        # conved_n = [batch size, n_filters, sent len - filter_sizes[n] + 1]

        pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved]

        # pooled_n = [batch size, n_filters]

        cat = self.dropout(torch.cat(pooled, dim=1))

        # cat = [batch size, n_filters * len(filter_sizes)]

        return self.fc(cat)

最后，可以训练模型并进行预测：

import torch.optim as optim

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

BATCH_SIZE = 64

train_iterator, valid_iterator, test_iterator = BucketIterator.splits(
    (train_data, valid_data, test_data),
    batch_size=BATCH_SIZE,
    device=device)

INPUT_DIM = len(TEXT.vocab)
EMBEDDING_DIM = 100
N_FILTERS = 100
FILTER_SIZES = [3, 4, 5]
OUTPUT_DIM = 1
DROPOUT = 0.5

model = CNN(INPUT_DIM, EMBEDDING_DIM, N_FILTERS, FILTER_SIZES, OUTPUT_DIM, DROPOUT)

optimizer = optim.Adam(model.parameters())

criterion = nn.BCEWithLogitsLoss()

model = model.to(device)
criterion = criterion.to(device)

def binary_accuracy(preds, y):
    rounded_preds = torch.round(torch.sigmoid(preds))
    correct = (rounded_preds == y).float()
    acc = correct.sum() / len(correct)
    return acc

def train(model, iterator, optimizer, criterion):
    epoch_loss = 0
    epoch_acc = 0

    model.train()

    for batch in iterator:
        optimizer.zero_grad()

        predictions = model(batch.text).squeeze(1)

        loss = criterion(predictions, batch.label)

        acc = binary_accuracy(predictions, batch.label)

        loss.backward()

        optimizer.step()

        epoch_loss += loss.item()
        epoch_acc += acc.item()

    return epoch_loss / len(iterator), epoch_acc / len(iterator)

def evaluate(model, iterator, criterion):
    epoch_loss = 0
    epoch_acc = 0

    model.eval()

    with torch.no_grad():
        for batch in iterator:
            predictions = model(batch.text).squeeze(1)

            loss = criterion(predictions, batch.label)

            acc = binary_accuracy(predictions, batch.label)

            epoch_loss += loss.item()
            epoch_acc += acc.item()

    return epoch_loss / len(iterator), epoch_acc / len(iterator)

N_EPOCHS = 5

for epoch in range(N_EPOCHS):
    train_loss, train_acc = train(model, train_iterator, optimizer, criterion)
    valid_loss, valid_acc = evaluate(model, valid_iterator, criterion)

    print(f'Epoch: {epoch+1:02}')
    print(f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%')
    print(f'\t Val. Loss: {valid_loss:.3f} |  Val. Acc: {valid_acc*100:.2f}%')

test_loss, test_acc = evaluate(model, test_iterator, criterion)

print(f'Test Loss: {test_loss:.3f} | Test Acc: {test_acc*100:.2f}%')