Views
No views yet
0: 工作邮件 (Work Email)
1: 个人邮件 (Personal Email)
2: 促销邮件 (Promotional Email)
3: 垃圾邮件 (Spam Email)
4: 通知邮件 (Notification Email)
5: 其他邮件 (Other Email)1from transformers import MobileBertForSequenceClassification, MobileBertTokenizer
2import torch
3
4# 加载模型和tokenizer
5model = MobileBertForSequenceClassification.from_pretrained('your-username/email-classifier-chinese')
6tokenizer = MobileBertTokenizer.from_pretrained('your-username/email-classifier-chinese')
7
8# 预测示例
9def predict_email_category(text):
10 inputs = tokenizer(
11 text,
12 return_tensors='pt',
13 truncation=True,
14 padding='max_length',
15 max_length=128
16 )
17
18 with torch.no_grad():
19 outputs = model(**inputs)
20 predictions = torch.softmax(outputs.logits, dim=-1)
21 predicted_class = torch.argmax(predictions, dim=-1).item()
22
23 labels = {
24 0: "工作邮件",
25 1: "个人邮件",
26 2: "促销邮件",
27 3: "垃圾邮件",
28 4: "通知邮件",
29 5: "其他邮件"
30 }
31
32 confidence = predictions[0][predicted_class].item()
33 return labels[predicted_class], confidence
34
35# 使用示例
36email_text = "恭喜您中奖了！点击链接领取奖品。"
37category, confidence = predict_email_category(email_text)
38print(f"邮件类型: {category}, 置信度: {confidence:.3f}")
39# 输出: 邮件类型: 促销邮件, 置信度: 0.9201from transformers import pipeline
2
3classifier = pipeline(
4 "text-classification",
5 model="your-username/email-classifier-chinese",
6 tokenizer="your-username/email-classifier-chinese"
7)
8
9result = classifier("您好，请查收今天的工作报告。")
10print(result)1@misc{chinese-email-classifier-2024,
2 title={Chinese Email Classification Model Based on MobileBERT},
3 author={Your Name},
4 year={2024},
5 publisher={Hugging Face},
6 journal={Hugging Face Model Hub},
7 howpublished={\\url{https://huggingface.co/your-username/email-classifier-chinese}}
8}