PaddleOCR

PaddleOCR copied to clipboard

ImportError: cannot import name '_switch_declarative_mode_guard_' from 'paddle.fluid.dygraph.base' (/usr/local/lib/python3.7/dist-packages/paddle/fluid/dygraph/base.py)

1

环境为ppocr docker 镜像2.1.3-gpu-cuda11.2-cudnn8容器环境，正常训练没有问题，但是根据官方文档进行量化就报错了，量化命令为python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o Global.save_model_dir=./output/quant_model_distill/ - 系统环境/System Environment： - 版本号/Version：Paddle： PaddleOCR：2.6 - 问题相关组件/Related components： paddleslim 2.3.2 - 运行指令/Command Code：python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o Global.save_model_dir=./output/quant_model_distill/ - 完整报错/Complete Error...

wangyang581

弯曲文本识别训练问题

7

  是需要修改，paddlepaddle不支持uint8格式的数据进行计算？

xialei2821212670

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 11 x64 - 版本号/Version：Paddle：2.3.2 PaddleOCR：2.6.01 问题相关组件/Related components： - 运行指令/Command Code： - 完整报错/Complete Error Message： I fine tuned...

rubensanchezrivero

PPOCRLabel支持关系抽取（relation extration)

3

可否在PPOCRLabel kie功能中添加关系标注功能？现在有点不方便

zhangluustb

SVTR 轉 onnx 後，inference 的結果變成空字串

9

- System Environment: python 3.6.13 - Version:   - 运行指令/Command Code： - yaml 檔 - https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/configs/rec/rec_svtrnet_ch.yml - 轉換模型的方法 - 基本上是參考: https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/deploy/paddle2onnx/readme.md  如果使用 export_model.py 預測出來的會是  結果如下: ...

708kelly

replace python-Levenshtein

1

Python-Levenshtein is GPL licensed, which is not compatible with the Apache license. This PR replaces python-levenshtein with the MIT licensed library rapidfuzz.

ghost

#Error from using custom dataset, every time I tried to use my dataset this error always occur

2

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：Google colab - 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：paddleocrv3 - 运行指令/Command Code：!python3 tools/train.py -c configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml -o Global.pretrained_model=./pretrain_models/en_PP-OCRv3_rec_train/best_accuracy - 完整报错/Complete Error...

Yosiiiiiiiiiiiiiiii

PPOCRV3文本识别精度低

7

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：Paddle：release/2.6 - PaddleOCR： 问题相关组件/Related components：ppocr_v3_rec - 运行指令/Command Code： - python tools/infer/predict_system.py --image_dir="******" --det_model_dir="./output/save_det_inference/" --rec_model_dir="./output/save_rec_inference/Student" --rec_image_shape="3, 48,...

engrwuang

Update dependency attrdict to attrdict3

1

haobibo

EAST text detection with tensorrt

3

Hi I am trying to convert this [det_r50_vd_east_v2.0_train](wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar) into `inference` model and run with `tensorrt` flag. Input image size is - 512 X 512 X 3 I am facing...

QuickLearner171998