PaddleOCR
PaddleOCR copied to clipboard
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and de...
What training data was used to produce the multilingual detection models? I have trained DB/DB++ models with MLT but was wondering if additional data sets were used in training the...
I would like to ask does StyleText support sentence inputs (document style rather than single words from street views) with spaces between them? or would you have plans on that,...
 安装的是这个配置  服务器  有大神知道是什么原因吗
相比之前的版本,中文繁体识别chinese_cht_PP-OCRv3_rec模型,经过测试不再适配“竖排文字”的识别。虽横排效果提升,但竖排效果很差(几乎不能识别)。 也经常看论坛,发现大家应用繁体字模型还是挺多的,而其实用到繁体字模型的场景多是竖排情况,比如古籍的识别等等。 所以,是否可以优化一下该问题。
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:Windows - 版本号/Version:Paddlepaddle:2.3.2 PaddleOCR:2.6.01 PPOCRLabel 2.1.1 问题相关组件/Related components: - 运行指令/Command Code:PPOCRLabel - 完整报错/Complete Error Message: 
win11 paddlenlp 2.3.1 paddleocr 2.5.0.3 paddlepaddle-gpu 0.0.0.post110 ser_vi_layoutxlm_xfund_zh.yml Architecture: model_type: kie algorithm: &algorithm "LayoutXLM" Transform: Backbone: name: LayoutXLMForSer pretrained: true checkpoints: # one of base or vi mode: vi num_classes:...

与手机联调,程序能跑通,识别结果只有一个字? 
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment: - 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components: - 运行指令/Command Code: - 完整报错/Complete Error Message:C++ Traceback (most recent call last):...
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:centos - 版本号/Version:Paddle:develop PaddleOCR: 2.6 问题相关组件/Related components: - 运行指令/Command Code: 2.2.1 图像方向分类+版面分析+表格识别 import os import cv2 from paddleocr...