PaddleOCR

PaddleOCR copied to clipboard

PPStructure missing text that PaddleOCR do not miss

7

#### 问题描述 / Problem Description PPStructure missing text that PaddleOCR do not miss #### 运行环境 / Runtime Environment - OS: - Paddle: - PaddleOCR: #### 复现代码 / Reproduction Code PaddleOCR(lang='en',...

omeruth

Can't Run the model on GPU,but CPU is fine. (error code is 126)

4

#### 问题描述 / Problem Description #### 运行环境 / Runtime Environment - OS:windows - Paddle:follow the quick start - PaddleOCR:follow the quick start #### 复现代码 / Reproduction Code 皆按照quickstart的步驟進行 #### 完整报错...

B1029038

执行paddleocr报ImportError

2

#### 问题描述 / Problem Description 执行 paddleocr --image_dir ~/hobby/test/1.png --use_angle_cls true --use_gpu false 命令报错，如下： ```log Error: Can not import paddle core while this file exists: /Users/janu/.local/share/virtualenvs/py3/lib/python3.11/site-packages/paddle/base/libpaddle.so Traceback (most recent call...

socay1

File "tools/infer_kie_token_ser_re.py", line 223, in <module> result_key[ocr_info_head['text']] = ocr_info_tail['text'] KeyError: 'text'

2

#### 问题描述 / Problem Description #### 运行环境 / Runtime Environment - OS: - Paddle: - PaddleOCR: #### 复现代码 / Reproduction Code #### 完整报错 / Complete Error Message #### 可能解决方案 /...

Unlicensed-driver-ljx

paddle_serving部署教程中，模型转换代码实效。

2

#### 问题描述 / Problem Description paddle_serving部署教程中，下载完推理模型，进行转换的时候，因为ocr更新至2.8,paddple更新至2.6,转换脚本失效。 paddle的fluid时效，替换成base后，仍有很多地方失效，导致教程不能进行下去。 有py3.9能用的最新的转换脚本吗？ #### 运行环境 / Runtime Environment - OS:ubuntu22.04 - Paddle:2.6.0 gpu - PaddleOCR:2.8.0 #### 复现代码 / Reproduction Code # 转换检测模型 python3 -m paddle_serving_client.convert...

greatliu

存在内存泄露

4

#### 问题描述 / Problem Description 存在内存泄露 #### 运行环境 / Runtime Environment - OS: Ubuntu 22.4 - Paddle:2.6.1 - PaddleOCR:2.8.0 #### 复现代码 / Reproduction Code from paddleocr import PaddleOCR from loguru...

XueKX

#### 问题描述 / Problem Description 执行： python tools/infer_vqa_token_ser_re.py -c configs/vqa/re/layoutxlm_sfz.yml -o Architecture.Backbone.checkpoints=output/re_layoutxlm_sfz/best_accuracy Global.infer_img=D:/projpython/paddlestudy/ocrtable/sfzlink/ocr/val_data/image/ -c_ser configs/vqa/ser/layoutxlm_sfz.yml -o_ser Architecture.Backbone.checkpoints=output/ser_layoutxlm_sfz/best_accuracy 输出：infer_results.txt D:/projpython/paddlestudy/ocrtable/sfzlink/ocr/val_data/image/0040.jpg {"ser_result": []} 数组是空的，关联没有显示出来 #### 运行环境 / Runtime Environment - OS: windows...

shiwenliang

### 🔎 Search before asking - [X] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report. - [X] I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no...

skyimager

paddleocr 2.8.1 paddlepaddle-gpu 2.6.1 占用大量显存并且只增不减，很快cuda oom

7

### 🔎 Search before asking - [X] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report. - [X] I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no...

purplesword

### 🔎 Search before asking - [X] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report. - [X] I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no...

umarbutler