PaddlePaddle/PaddleOCR
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 deployment among server, mobile, embedded and IoT devices)
PythonApache-2.0
Pinned issues
Issues
- 3
[branch 2.6.1 & 2.7.1]PyMuPDF install failed(pip install -r requirements.txt)
#12827 opened by kelvinji2009 - 2
打开TensorRT不使用动态Shape的情况下 识别速度越来越慢
#12752 opened by hangLt333 - 0
使用pyinstaller打包后的程序无法运行
#12822 opened by AlexWxW - 4
- 0
- 0
Support to load model in a local directory
#12775 opened by SWHL - 2
在打开TensoeRT后 运行到Run Paddle-TRT Dynamic Shape mode. 时会卡很久
#12590 opened by hangLt333 - 5
OCR system producing no output when run on GPU
#12551 opened by emily-bianchi - 2
paddleocr 在华为910b的npu上跑很慢且只跑了一张卡
#12531 opened by danyXu - 0
自己数据集训练效果很差
#12765 opened by h4444433333 - 1
Cannot run "only" text detection
#12761 opened by PierreCarceller - 2
Android PP-OCRv3
#12662 opened by Alexng2024 - 2
运行PaddleOCR示例代码报错 TypeError: TextSystem.call() takes from 2 to 3 positional arguments but 4 were given
#12756 opened by confuse05 - 0
表格识别内容没有正常转义 '<' '>'
#12509 opened by heweisheng - 3
paddle2onnx现已不支持--input_shape_dict="{'x':[-1,3,x,x}"参数使用
#12743 opened by Mrxuba - 11
Using multiple dictionaries with paddleocr
#12553 opened by saanvib13 - 1
ppocrv4 det 微调
#12515 opened by rongyixiao180319 - 4
svtr yml用来训练,爆显存,batch_size=1也不行
#12517 opened by nissansz - 4
paddleocr Out of memory error
#12606 opened by kennyLSN - 4
按照示例Python代码。进行PDF类型的版面识别报错,但是使用命令行正常
#12741 opened by username12021202 - 4
使用paddle-ocr和PyMuPDF识别PDF文件的问题
#12607 opened by AHPUymhd - 3
Predict SER, RE KIE with my ocr
#12644 opened by minhduc01168 - 1
有没有更多印章数据集下载链接?能分享一下吗?谢谢
#12643 opened by LMR2018 - 0
resnet34 rec模型如何修改ctcloss以改善识别结果
#12648 opened by nissansz - 3
运行示例代码报错:FatalError: `Segmentation fault` is detected by the operating system.
#12647 opened by Alexia1994 - 1
rec_svtrnet_ch.yml 配置训练的图片,识别报错
#12646 opened by nissansz - 2
版面分析文本块未识别
#12642 opened by PureWaterCatt - 1
Could not load library libcublasLt.so.12. Error: libcublasLt.so.12: cannot open shared object file: No such file or directory
#12641 opened by WingI9B1 - 1
表格识别的几个问题,希望有负责的这部分功能的大佬可以帮忙解答!!!
#12608 opened by liuzhipengchd - 5
PaddleOCR not working in a multiprocessing scenario
#12609 opened by subhankardori - 4
按照教程将SER+RE串联执行,代码报错 argument 'x' (position 0) must be list of Tensors, but got empty list
#12570 opened by username12021202 - 0
svtr UIM:无标注数据挖掘方案吗,这个在训练时是要怎么弄?如果我用普通图片+label有什么影响吗?
#12595 opened by nissansz - 2
./configs/rec/rec_svtrnet_ch.yml 这个配置可以训练 ./configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml 这个配置即使设置batch size =1也爆显存,怎么修改这个配置让其能训练?
#12584 opened by nissansz - 1
max_text_length 这个默认的25 也可以识别单行文字超过25个字符的图片,那这个参数为什么要设置?
#12586 opened by nissansz - 1
4090显卡跑起来与CPU平均测试速度有1倍差距,这个正常吗?
#12587 opened by tang9527 - 1
svtr训练速度比resnet34 慢很多?同等配置,有没有办法加速?
#12588 opened by nissansz - 5
ch_PP-OCRv4_rec_svtr_large.yml训练导出的模型,使用predict_rec.py预测宽度比较大的图片时出现(InvalidArgument) Broadcast dimension mismatch
#12440 opened by LMR2018 - 5
Notice of PPOCRLabel and StyleText Project Migration
#12508 opened by GreatV - 1
编译安装paddle-custom-npu-0.0.0后使用paddleocr特别慢
#12567 opened by fallbernana123456 - 4
报错-非法指令 coredump
#12550 opened by guonaihong - 5
cudaErrorInitializationError at ../paddle/phi/backends/gpu/cuda/cuda_info.cc:178
#12525 opened by sheiy - 7
pdf扫描件表格识别不准确,如何优化?
#12523 opened by PureWaterCatt - 2
Error about ppocrlabel, when start ppocrlabl
#12522 opened by nam157 - 0
PP-ChatOCRv2-common 默认的提示词规则是什么样的呢?以及数据微调格式
#12526 opened by cqray1990 - 1
How to recognize the digital numbers in the rectangle box with paddleocr?
#12518 opened by githubthunder - 3
server模型推理出错(core dumped)
#12443 opened by wanggp01 - 5
长文本行识别,偶尔会出现单个字符被识别成2个相同字符的错误,比如,只有一个"一",识别成2个了,怎样改善?
#12506 opened by nissansz - 0
How to find rotated image.
#12448 opened by Dineshkumar-Anandan-ZS0367 - 1
Dynamic Merging of Word Bounding Boxes
#12169 opened by satvik-27199 - 1