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

如何提升版面分析模型精度 #28

Open
Harryoung opened this issue Sep 8, 2023 · 1 comment
Open

如何提升版面分析模型精度 #28

Harryoung opened this issue Sep 8, 2023 · 1 comment

Comments

@Harryoung
Copy link
Owner

我们提供了issue bot来帮助你解答问题,你是否想要它来解答(请填写yes/no)?/We provide issue bot to solve issues, do you want it? (Please write yes/no):yes

请注意:issue bot基于大语言模型实现,其回答仅供参考。目前issue bot尚不能解析issue中的图片。/Please note: The issue bot is implemented based on large language models, and its answers are for reference only. Currently the issue bot cannot parse images in issues.

请在这里描述你的问题/Please describe your issue here:
在CDLA数据集上进行训练测试,效果不是很理想,有人能帮解决一下吗

@llm-issue-bot
Copy link

llm-issue-bot bot commented Sep 8, 2023

Issue Response

  • Introduction: Thanks for opening this issue, I am the issue bot that will help you with your questoins!
  • 🎯 First round response: The answer to your question is:

在CDLA数据集上进行训练测试,效果不是很理想。在CDLA数据集上的消融实验结果如下:

  • 在CDLA数据集上,使用PP-YOLOv2策略的mAP为84.70%。
  • 在CDLA数据集上,使用PP-PicoDet-LCNet2.5x(800*608)策略的mAP为87.80%。
  • 在CDLA数据集上,使用PP-PicoDet-LCNet1.0x(800*608)策略的mAP为84.50%。
  • 在CDLA数据集上,使用PP-PicoDet-LCNet1.0x(800*608) + FGD策略的mAP为86.80%。

在表格数据集上的消融实验结果如下:

  • 在表格数据集上,使用PP-YOLOv2策略的mAP为91.30%。
  • 在表格数据集上,使用PP-PicoDet-LCNet2.5x(800*608)策略的mAP为95.90%。
  • 在表格数据集上,使用PP-PicoDet-LCNet1.0x(800*608)策略的mAP为95.20%。
  • 在表格数据集上,使用PP-PicoDet-LCNet1.0x(800*608) + FGD策略的mAP为95.70%。

Relevant Sources

https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/ppstructure/layout/README_ch.md, https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/applications/轻量级车牌识别.md, https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/ppstructure/docs/PP-StructureV2_introduction.md

How to use

My answer may not be accurate. I suggest you refer to relevant sources to make a comprehensive judgment.
To invoke me for more questions, add a comment using following command:
@llm-issue-bot <QUESTION>

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

No branches or pull requests

1 participant