使用XLNet进行情感分析-设置正确的整形参数

from transformers import XLNetTokenizer, XLNetForSequenceClassification
import torch

# 加载预训练的XLNet模型和分词器
model_name = 'xlnet-base-cased'
tokenizer = XLNetTokenizer.from_pretrained(model_name)
model = XLNetForSequenceClassification.from_pretrained(model_name)

# 示例文本
text = "I really love this product! It's amazing."

# 对文本进行编码
inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True, max_length=128)

# 设置正确的整形参数
batch_size = inputs['input_ids'].size(0)
sequence_length = inputs['input_ids'].size(1)
embedding_dim = model.config.hidden_size

# 打印整形参数
print(f"Batch size: {batch_size}")
print(f"Sequence length: {sequence_length}")
print(f"Embedding dimension: {embedding_dim}")

# 进行情感分析
outputs = model(**inputs)
logits = outputs.logits
predicted_class = torch.argmax(logits, dim=1).item()

print(f"Predicted sentiment: {'Positive' if predicted_class == 1 else 'Negative'}")