Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,17 @@ language:
|
|
| 4 |
- zh
|
| 5 |
---
|
| 6 |
|
| 7 |
-
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- zh
|
| 5 |
---
|
| 6 |
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
模型输出标签有7个，对应关系如下
|
| 10 |
+
```
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "OTHERS",
|
| 13 |
+
"1": "B-HEADER",
|
| 14 |
+
"2": "I-HEADER",
|
| 15 |
+
"3": "B-QUESTION",
|
| 16 |
+
"4": "I-QUESTION",
|
| 17 |
+
"5": "B-ANSWER",
|
| 18 |
+
"6": "I-ANSWER"
|
| 19 |
+
}
|
| 20 |
+
```
|