PaddlePaddle/PaddleX

paddlex调用paddleocr通用表格识别v2产线如何自定义更多参数

Open

#4871 opened on Dec 30, 2025

View on GitHub
 (0 comments) (0 reactions) (1 assignee)Python (4,520 stars) (894 forks)batch import
help wanted

Description

在使用paddleocr通用表格识别v2产线时，使用版面区域检测，表格单元格检测等模块时候如何自定义修改置信度阈值，layout_unclip_ratio等参数，在这些的单模块使用教程中是有这些参数的，说不指定将默认使用PaddleX官方模型配置，这些配置文件在哪里可以找到呢？

Contributor guide

Tech stack
python
Domain
machine learning
Issue type
documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
needs maintainer response
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Python basicsPaddleX understanding
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70
Research direction
Investigate the PaddleX repository's configuration files for the table recognition v2 pipeline. The default parameters such as confidence thresholds and layout unclip ratio are likely stored in YAML files under `paddlex/configs/` or `paddlex/pipelines/`. The maintainer should respond with the exact file path and explain how to override these parameters when instantiating the pipeline.