Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

如何提高 tablemaster 的计算速度 #1408

Closed
boboyunz opened this issue Jan 5, 2025 · 10 comments
Closed

如何提高 tablemaster 的计算速度 #1408

boboyunz opened this issue Jan 5, 2025 · 10 comments
Labels
enhancement New feature or request

Comments

@boboyunz
Copy link

boboyunz commented Jan 5, 2025

我分别测四了 rapid_table 、tablemaster、struct_eqtable 对于复杂的表格 目前tablemaster 效果是最好的 但是速度确实很慢 识别一个表格需要200-600秒 目前paddlepaddle 用的CPU 但是minerU 开启了CUDA 请高手指点 如何能够提高 tablemaster 的计算速度?
目前cuda的版本是12.2 但是paddlepaddle -gpu的版本目前最高支持CUDA11.8 所以暂时还没有降低CUDA的版本,主要考虑tablemaster 应该不依赖paddlepaddle -gpu 这个存疑。
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
还没有解决tablemaster 的速度问题

Describe the solution you'd like

A clear and concise description of what you want to happen.
有效的提高tablemaster 的计算效率 如何利用GPU加速

Describe alternatives you've considered
通过配置强制tablemaster 使用GPU

Additional context
提供更多细节
Add any other context or screenshots about the feature request here.
image

image

@boboyunz boboyunz added the enhancement New feature or request label Jan 5, 2025
@myhloli
Copy link
Collaborator

myhloli commented Jan 5, 2025

你需要安装paddlepaddle-gpu包以实现tablemaster的加速

@boboyunz
Copy link
Author

boboyunz commented Jan 5, 2025

python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu123
我用这句指令安装paddlepaddle-gpu 结果报错了
image
image
有高手遇见过这样的问题吗 请指点

@myhloli
Copy link
Collaborator

myhloli commented Jan 5, 2025

按教程用cu118的paddlegpu

@boboyunz
Copy link
Author

boboyunz commented Jan 5, 2025

我本地的CUDA 12.6 是否可以用
是不是说 CUDA 的环境 必须改成11.8 请指点?

@myhloli
Copy link
Collaborator

myhloli commented Jan 5, 2025

不影响,paddle的cuda是独立的

@boboyunz
Copy link
Author

boboyunz commented Jan 5, 2025

python -m pip install paddlepaddle-gpu==3.0.0b2 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/ 我用这个版本测试成功了
image
谢谢

@boboyunz
Copy link
Author

boboyunz commented Jan 5, 2025

计算复杂表格的时候会报错
image
image

@boboyunz
Copy link
Author

boboyunz commented Jan 5, 2025

image
image
image
image
image

@myhloli
Copy link
Collaborator

myhloli commented Jan 5, 2025

tablemaster在某些情况下会有不稳定的问题,目前推荐使用rapidtable来解析表格

@myhloli myhloli closed this as completed Jan 5, 2025
@boboyunz
Copy link
Author

boboyunz commented Jan 5, 2025

但是tablemaster对复杂表格识别效果很好,值得优化一下

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants