transformer 文本二分类

Transformer是一种用于自然语言处理任务的深度学习模型，它在文本分类任务中表现出色。下面是使用Transformer进行文本二分类的示例代码：

import torch
import torch.nn as nn
import torch.optim as optim
from torchtext.data import Field, TabularDataset, BucketIterator
from torch.nn import TransformerEncoder, TransformerEncoderLayer

# 定义模型
class TransformerClassifier(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim, n_layers, n_heads, dropout):
        super().__init__()
        self.embedding = nn.Embedding(input_dim, hidden_dim)
        self.encoder_layer = TransformerEncoderLayer(hidden_dim, n_heads, hidden_dim, dropout)
        self.encoder = TransformerEncoder(self.encoder_layer, n_layers)
        self.fc = nn.Linear(hidden_dim, output_dim)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, text):
        embedded = self.embedding(text)
        embedded = embedded.permute(1, 0, 2)
        output = self.encoder(embedded)
        output = output.permute(1, 0, 2)
        pooled = torch.mean(output, dim=1)
        pooled = self.dropout(pooled)
        return self.fc(pooled)

# 数据预处理
TEXT = Field(tokenize='spacy', lower=True)
LABEL = Field(sequential=False, is_target=True)

fields = [('text', TEXT), ('label', LABEL)]
train_data, test_data = TabularDataset.splits(
    path='data',
    train='train.csv',
    test='test.csv',
    format='csv',
    fields=fields,
    skip_header=True
)

TEXT.build_vocab(train_data, min_freq=2)
LABEL.build_vocab(train_data)

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

train_iterator, test_iterator = BucketIterator.splits(
    (train_data, test_data),
    batch_size=64,
    device=device
)

# 模型训练
input_dim = len(TEXT.vocab)
output_dim = 2
hidden_dim = 256
n_layers = 2
n_heads = 8
dropout = 0.2

model = TransformerClassifier(input_dim, hidden_dim, output_dim, n_layers, n_heads, dropout).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters())

def train(model, iterator, optimizer, criterion):
    model.train()
    epoch_loss = 0
    epoch_acc = 0
    
    for batch in iterator:
        optimizer.zero_grad()
        text = batch.text
        label = batch.label
        predictions = model(text).squeeze(1)
        loss = criterion(predictions, label)
        acc = binary_accuracy(predictions, 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):
    model.eval()
    epoch_loss = 0
    epoch_acc = 0
    
    with torch.no_grad():
        for batch in iterator:
            text = batch.text
            label = batch.label
            predictions = model(text).squeeze(1)
            loss = criterion(predictions, label)
            acc = binary_accuracy(predictions, label)
            epoch_loss += loss.item()
            epoch_acc += acc.item()
        
    return epoch_loss / len(iterator), epoch_acc / len(iterator)

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

N_EPOCHS = 10

best_valid_loss = float('inf')

for epoch in range(N_EPOCHS):
    train_loss, train_acc = train(model, train_iterator, optimizer, criterion)
    valid_loss, valid_acc = evaluate(model, test_iterator, criterion)
    
    if valid_loss < best_valid_loss:
        best_valid_loss = valid_loss
        torch.save(model.state_dict(), 'transformer_model.pt')
    
    print(f'Epoch: {epoch+1:02} | Train Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}% | Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:.2f}%')

# 加载模型并进行预测
model.load_state_dict(torch.load('transformer_model.pt'))

def predict_sentiment(model, sentence):
    model.eval()
    tokenized = [tok.text for tok in spacy_en.tokenizer(sentence)]
    indexed = [TEXT.vocab.stoi[t] for t in tokenized]
    tensor = torch.LongTensor(indexed).unsqueeze(1).to(device)
    prediction = torch.sigmoid(model(tensor))
    return prediction.item()

# 示例预测
sentence = "This movie is great!"
prediction = predict_sentiment(model, sentence)
print(f'Sentence: {sentence} | Prediction: {prediction:.4f}')

请注意，上述代码中的数据集是使用torchtext库加载的csv文件，其中包含两列：text和label。你需要将你的文本数据准备成类似的格式，并将其保存为train.csv和test.csv文件。