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...
Hello dear paddleocr team . Paddle2onnx exports all svtr (tiny,small,base,large) models ... but only svtr tiny (onnx) output is normal , Other models (small,base,large) output is empty after exporting to...
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:
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:Ubuntu 20 - 版本号/Version:Paddle: 2.6 PaddleOCR:2.6 问题相关组件/Related components: Dec/Rec - 运行指令/Command Code: ``` ocr = PaddleOCR(use_angle_cls=True, cls=True, use_gpu=True,...
你好我想我想问下,怎么把印章上的黑色字体去掉尼,然后提取出印章,我试用 了你们官方的印章识别,是很好的把印章的内容识别出来了,并没有收到黑色干扰字的影响?有这方面的方法吗?
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:Linux - 版本号/Version:Paddle: PaddleOCR: PaddlePaddle2.3 PaddleOCR2.5 想体验一下ppocrv3升级带来的提升,请问ppocrv3可以使用python pipeline部署吗
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: ubuntu22, python3.7, CUDA11.7 - 版本号/Version:Paddle:2.3.2 PaddleOCR: 2.6.0 问题相关组件/Related components:paddleocr - 运行指令/Command Code:paddleocr --image_dir ./testdata/12.png --use_angle_cls true --lang...
## 问题发送过程:用PaddleDetection和PaddleOCR同时使用,将PaddleDetection检测结果传入PaddleOCR得到期望数据。系统开始一段时间正常运行,输出结果比较理想,几分钟后程序运行到`perdict_system_1780.main(utility.parse_args(), image)`[perdict_system_1780代码](https://github.com/Jeck-Liu-Create/paddle-issues/blob/main/predict_system_1780.py),[utility代码](https://github.com/Jeck-Liu-Create/paddle-issues/blob/main/utillty.py) ## paddle版本: paddlepaddle-gpu==2.2.2 cudatoolkit=11.2 - Paddleocr:2.3 - PaddleDetection:2.3 ## 主机配置: - 系统:ubuntu 20.04 - GPU:3060 lp 12G - CUDA:11.2 - CUDNN:8.1.1 - Driver Version::470.103.01 ### 错误代码提示: ```...
数据集使用的是SynthText/MJsynth/Synthetic-Chinese-String-Dataset CRNN训练验证集能达到94%,而ppocr-v3只能达到90% config.yml ``` Global: debug: false use_gpu: true epoch_num: 500 log_smooth_window: 20 print_batch_step: 10 save_epoch_step: 1 eval_batch_step: - 0 - 2000 cal_metric_during_train: true pretrained_model: null checkpoints: null save_inference_dir: null...