PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition #3510
Replies: 9 comments 15 replies
-
怎么回事,更新完了
请问我该怎么解决? |
Beta Was this translation helpful? Give feedback.
-
不同的OCR产线的区别是否是配置文件呢? |
Beta Was this translation helpful? Give feedback.
-
请问处理pdf文件,假如文件中既有文字的部分,也有图片的部分,内部是如何处理的?全部转换成图片再ocr吗,还是有所区分呢? |
Beta Was this translation helpful? Give feedback.
-
模型微调方法还会公开吗?今天用通用ocr产线+qwen已经比表格识别v2产线效果好了 感觉传统kie的模型已经没必要炼了.... 如果不是为了corner case做调整基本prompt写好就行了 |
Beta Was this translation helpful? Give feedback.
-
要是只想做文字识别功能如何做?在ocr文件将文本检测关闭吗? |
Beta Was this translation helpful? Give feedback.
-
请问如何快速处理很大的数据量呢,比如4GPU,或者拉大batchsize? |
Beta Was this translation helpful? Give feedback.
-
问一哈,怎么生成双层pdf呢,我们的代码中是不是已经集成了 |
Beta Was this translation helpful? Give feedback.
-
遇到一个问题 windows 用户 名称是中文的时候找不到对应的模型文件,有什么环境变量或者什么东西可以修改模型地址吗 paddlex --pipeline OCR --input C:/Users/张宏/Pictures/tp.png --use_doc_orientation_classify False --use_doc_unwarping False --use_textline_orientation False --save_path ./output --device gpu:0 |
Beta Was this translation helpful? Give feedback.
-
对于表格结构识别的结果,只有可视化的结果吗,如果我想要得到识别出来的每个单元格(包括空白的单元格)的坐标信息,应该如何处理 |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition
https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/table_recognition.html
Beta Was this translation helpful? Give feedback.
All reactions