---
tags:
- generated_from_keras_callback
- classifier
- adult-content-identify-text
- adult
- adult-content
- text-classifier 
- text
- classifier
model-index:
- name: adult-content-classifier-text
  results: []
pipeline_tag: text-classification
widget:
- text: 情趣睡衣 性感睡衣 角色扮演 惹火 緊身連身 漆皮膠衣 黑 L
  example_title: adult_成人商品標題
- text: 男平織運動外套-立領外套 慢跑 路跑 藍黑螢光黃 L
  example_title: regular_一般商品標題
- text: 'Passionate Embrace: Cross-Laced Sexy Silky Lingerie Sleepwear, White'
  example_title: adult_product
- text: >-
    Men's Plain Weave Sports Jacket - Stand Collar Jacket for Jogging and
    Running, Blue-Black-Fluorescent Yellow, Size L
  example_title: regular_product
license: mit
language:
- en
- zh
- ko
- ja
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->

# adult-content-identify-text

Support languages: English, Chinese (both CN/TW), Japanese, Korean

Determine whether online sales products are adult content. Input: text of product title or description, Output results 0: Unknown, 1: Adult Content, 2: General Merchandise.

判斷網路銷售商品是否屬於成人內容。輸入: 商品名稱文字，輸出結果: 0 未知, 1 成人內容, 2 一般商品。

# use transformers pipeline
```python
from transformers import pipeline, AutoConfig
pipe = pipeline("text-classification", model="jiechau/adult-content-identify-text")
config = AutoConfig.from_pretrained("jiechau/adult-content-identify-text")
label2id = config.label2id
id2label = config.id2label

#q = '男平織運動外套-立領外套 慢跑 路跑 藍黑螢光黃 L'
q = '情趣睡衣 性感睡衣 角色扮演 惹火 緊身連身 漆皮膠衣 黑 L'
result = pipe(q)
print(result)
print(label2id[result[0]['label']])
# [{'label': 'adult_成人商品', 'score': 0.9994813799858093}]
# 1
```

### Framework versions

- Transformers 4.37.1
- TensorFlow 2.15.0
- Datasets 2.17.0
- Tokenizers 0.15.1