PaddleOCR

PaddleOCR copied to clipboard

ch_PP-OCRv4_server检测不出灰烬的烬字

1

#### 问题描述 / Problem Description ch_PP-OCRv4_server模型检测不出灰烬的烬字，偶尔会识别成其他字，使用飞浆官网通用OCR体验也识别不出来 #### 运行环境 / Runtime Environment - OS: win10 - Paddle: 2.6.1 - PaddleOCR: 2.7.0.0 #### 复现代码 / Reproduction Code #### 完整报错 / Complete Error...

1822067490

svtr+stn，inference和onnx模型推理精度差异很大

4

#### 问题描述 / Problem Description 推理精度 #### 运行环境 / Runtime Environment - OS:linux - cuda:11.2 - python:3.7 - Paddle:2.4.2.post112 - PaddleOCR:2.6.1.0 - paddle2onnx:1.0.6 / 1.1.0 - onnxruntime:1.11.0 #### 复现代码 /...

Acheerfulloser

About the bug of paddleocr running with distributed.launch

5

#### 问题描述 / Problem Description 获取gpu id 的地方需要优化，paddle.distributed.launch 多卡调用paddleocr会导致模型只使用第一张卡运行？ #### 运行环境 / Runtime Environment - OS: - Paddle: - PaddleOCR: #### 复现代码 / Reproduction Code #### 完整报错 / Complete Error...

LDOUBLEV

### Discussed in https://github.com/PaddlePaddle/PaddleOCR/discussions/13227 Originally posted by **zhangtingyun** July 1, 2024 我更换飞浆的版面分析的模型 训练中文数据集 CDLA 但ap一直上不去，一直在80%左右，但官网的准确率不应该在 94%左右吗？ 配置如下： pretrain_weights: https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla.pdparams #pretrain_weights: output/best_model.pdparams weights: output/picodet_lcnet_x1_0_fgd_layout_cdla/model_final find_unused_parameters: True use_ema: true cycle_epoch: 10 snapshot_epoch:...

zhangtingyun

#### 问题描述 / Problem Description 训练文本检测模型，训练后的checkpoints模型与转换后的inference模型识别效果不一致 #### 运行环境 / Runtime Environment - OS: Windows10 - Paddle: 2.4.2 - PaddleOCR: 2.7.0 #### 复现代码 / Reproduction Code 训练：tools/train.py -c ./configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_student.yml 评估：tools/eval.py -c...

zhongmy20230403

..

1

LLotme

For seveRecRes, so that the cropped images are smooth, not inverted. If an area was incorrectly marked up, for example, the areas were highlighted not from the top left, but...

Azzer8

中文版面分析CDLA，自己训练出来的验证集bbox ap比官方的picodet_lcnet_x1_0_fgd_layout_cdla低好几个点

5

#### 中文版面分析CDLA，用官方demo，自己训练出来的bbox ap比官方的picodet_lcnet_x1_0_fgd_layout_cdla低好几个点/ Problem Description #### 运行环境 / Runtime Environment - OS:linux，2-V100-32G - Paddle:2.5.0 - PaddleOCR:2.7.0.3 没有使用FGD蒸馏训练，学习率等比率缩放了，验证集的bbox ap为0.806，请帮忙看看我的配置是否有问题，我试过num_classes: 10的，没有11类的高。另外也试过FGD蒸馏训练，也比较低。不知道哪里出了问题，是什么原因导致差了好几个点的AP。picodet_lcnet_x1_0_fgd_layout_cdla是否是不一样的配置或者不一样的数据？ 第100epoch：  ## picodet_lcnet_x1_0_layout_cdla.yml文件： ```yaml _BASE_: [ '../../../../runtime.yml', '../../_base_/picodet_esnet.yml', '../../_base_/optimizer_100e.yml',...

liaolinchun-AI

RE模型训练出错，谁能帮忙分析一下原因

12

#### 问题描述 / Problem Description Traceback (most recent call last): File "tools/train.py", line 208, in main(config, device, logger, vdl_writer) File "tools/train.py", line 180, in main program.train(config, train_dataloader, valid_dataloader, device, model,...

shiwenliang

The Korean language model fails to recognize '.' because it is missing.

4

### Discussed in https://github.com/PaddlePaddle/PaddleOCR/discussions/13144 Originally posted by **junhwan-lim** June 21, 2024 The Korean language model fails to recognize '.' because it is missing.

GreatV