PaddleOCR

PaddleOCR copied to clipboard

C++中使用Tensorrt推理报错

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：CUDA：10.2 CUDNN：8.1.1 Tensorrt：7.2.3.4 - 版本号/Version： PaddleOCR： release-2.4 - 下载的paddle_inference： GIT COMMIT ID: a5cf2e305b744e3ebd2f2210341f88d349d4ec5e WITH_MKL: ON WITH_MKLDNN: ON WITH_GPU:...

ainndejj11

PaddleOCR 2.5 版本 ，use_tensorrt=True 跑不通

40

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：ubuntu18.04 cuda 10.2 cudnn8 python3.7 tensorrt 7.2.3.4 - paddle2onnx 0.5 paddlehub 1.8.3 paddleocr 2.5.0.3 paddlepaddle-gpu 2.3.0 paddleslim 1.1.1...

shihaitao118

Updated WandbLogger to make uploading model checkpoints optional

3

This PR adds a minor patch to the WandbLogger integration to make saving model checkpoints to the W&B dashboard optional. To save checkpoints to the dashboard, the users just need...

manangoel99

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：2.4 Paddle： PaddleOCR： 问题相关组件/Related components： - 运行指令/Command Code： - 完整报错/Complete Error Message： 2022-07-28 08:33:01,043 Op(rec): 2022-07-28...

pooregg

limit maximum resizing ratio

2

limit max_wh_ratio as the ratio can be higher than max_wh_ratio. ``` resize_shape = (3,32, 320) wrong = np.zeros((32, 325, 3)) y= resize_norm_img_chinese(wrong, resize_shape)[0] y.shape = (3, 32, 325) ```

jinmingteo

PPOCRv3 slim模型有错误

3

我测试了一下，这个PPOCRv3的识别模型slim版识别出来不对，用原版就没问题（模型转换为lite nb模型）

shivabohemian

Module Not Found When Convert to exe file

1

Traceback (most recent call last): File "app.py", line 7, in File "", line 983, in _find_and_load File "", line 967, in _find_and_load_unlocked File "", line 677, in _load_unlocked File "PyInstaller\loader\pyimod02_importers.py",...

thein-htay-aung

det_mv3_east hmean ~95%, but very few text instances correctly detected

1

- 系统环境/System Environment：Debian 10, CUDA11.3, Nvidia V100 - 版本号/Version：paddlepaddle-gpu==2.0.0, PaddleOCR release==2.5 (cloned repo) - 运行指令/Command Code：python3 tools/infer/predict_det.py --image_dir="./test_data/test_images" --det_model_dir="./inference/det_mv3_east_3" --det_algorithm="EAST" I used the det_mv3_east configure file and changed only a...

gavinfaimdata

The yml name doesn't match the model's

4

https://github.com/PaddlePaddle/PaddleOCR/blob/9f05636ecdc244eed79c9d2b453ce11038bd012d/doc/doc_en/algorithm_rec_srn_en.md?plain=1#L26-L28 https://github.com/PaddlePaddle/PaddleOCR/blob/9f05636ecdc244eed79c9d2b453ce11038bd012d/doc/doc_ch/algorithm_rec_srn.md?plain=1#L26-L28 The yml file is `rec_r50_fpn_srn.yml`, which is inconsistent with `rec_r50_vd_srn_train.tar`.

thsno02

现在PPOCRv3 支持在Paddlelite 安卓端侧推理吗

20

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：安卓12 骁龙888 - 版本号/Version： PaddleOCR：2.5 PaddleLite 2.10 模型为ppocr官网直接下载的v3 nb格式模型，预测库为2.10 release inference_lite_lib.android.armv8.gcc.c++_shared.with_extra.with_cv 报错/Paddle-Lite: [F 6/17 14:14:10.792 ...CR/lite/Paddle-Lite/lite/core/program.cc:264 RuntimeProgram] Check...

zhang0227