PaddleX/latest/en/module_usage/tutorials/ocr_modules/text_recognition #4142
Replies: 8 comments 11 replies
-
现在只有mobile或者server模型了吗,类似PP-OCRv4_rec_infer的普通模型还有吗 |
Beta Was this translation helpful? Give feedback.
-
4.1.2 节中,数据校验 的 main.py 文件是哪个文件? |
Beta Was this translation helpful? Give feedback.
-
按照上面的教程训练PP-OCRv5_server_rec模型,各种报错,能提供更详细的训练教程吗 |
Beta Was this translation helpful? Give feedback.
-
在这个新版本里,文本识别模块 不需要指定识别相关的参数了么。比如图像输入尺寸什么的。 |
Beta Was this translation helpful? Give feedback.
-
在哪里可以配置ocr 识别的私有字典? |
Beta Was this translation helpful? Give feedback.
-
文本识别是否可以输入边界框,然后检测边界框中的文本。 |
Beta Was this translation helpful? Give feedback.
-
我有很多手写的文件照片,我发现直接使用PP-OCRv5_server_rec识别不准确,我是否应该参考本篇进行训练,比如我是用ppocrlabel标注500页照片,然后按照文档进行训练,我理解的这个对吗 |
Beta Was this translation helpful? Give feedback.
-
这个我没太理解,为什么一会用python脚本一会用命令行,这个能不能都在脚本内处理,搞得我有点乱呀 |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
PaddleX/latest/en/module_usage/tutorials/ocr_modules/text_recognition
https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/ocr_modules/text_recognition.html
Beta Was this translation helpful? Give feedback.
All reactions