Instructions to use yuyijiong/layoutlmv3-base-chinese-xfund with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yuyijiong/layoutlmv3-base-chinese-xfund with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="yuyijiong/layoutlmv3-base-chinese-xfund")# Load model directly from transformers import AutoProcessor, AutoModelForTokenClassification processor = AutoProcessor.from_pretrained("yuyijiong/layoutlmv3-base-chinese-xfund") model = AutoModelForTokenClassification.from_pretrained("yuyijiong/layoutlmv3-base-chinese-xfund") - Notebooks
- Google Colab
- Kaggle
在中文xfund上微调的layoutlmv3-chinese-base模型,可以对表格数据进行序列标注
模型的功能是:根据图片信息,对所有文字进行序列标注
模型需要输入以下信息:1.文档全部的文字(由其他ocr软件扫描得到) 2.体现文档结构的图片
模型输出标签有7个,对应关系如下
"id2label": {
"0": "OTHERS",
"1": "B-HEADER",
"2": "I-HEADER",
"3": "B-QUESTION",
"4": "I-QUESTION",
"5": "B-ANSWER",
"6": "I-ANSWER"
}
- others: 其他文字
- header:标题文字
- question:表头文字
- answer:表内容文字
- Downloads last month
- 62