adult-content-identify-image

(text version here 文字版本請參考 這裡)

Determine whether online sales products are adult content. Input: image content, 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。輸入圖片內容,輸出結果: 0 未知, 1 成人內容, 2 一般商品。

use transformers pipeline

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

q = 'https://xxx.xxx.xxx/images/xxx/xxx.webp'
q = 'https://xxx.xxx.xxx/images/xxx/xxx.jpg'
result = pipe(q)
print(result)
print(label2id[result[0]['label']])
# [{'label': 'adult_成人商品', 'score': 0.7516837120056152}, {'label': 'regular_一般商品', 'score': 0.2475457787513733}, {'label': 'unknown', 'score': 0.0007705678581260145}]
# 1
Downloads last month
31
Safetensors
Model size
85.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using jiechau/adult-content-identify-image 1