| license: cc-by-nc-sa-4.0 | |
| language: | |
| - zh | |
| 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：对含有表格的图片进行ocr，获得全部文字，然后根据图片信息，对所有文字进行序列标注 \ | |
| 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" | |
| } | |
| ``` |