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

paddleocr训练自己数据,文本检测不出结果! #12103

Closed
gengyanlei opened this issue May 13, 2024 · 5 comments
Closed

paddleocr训练自己数据,文本检测不出结果! #12103

gengyanlei opened this issue May 13, 2024 · 5 comments
Assignees

Comments

@gengyanlei
Copy link

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

  • 系统环境/System Environment:
  • 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:
  • 运行指令/Command Code:
  • 完整报错/Complete Error Message:

1.环境:
win10、gpu、cuda11.2、cudnn8.2、paddocr2.7
2.数据:
按照ppocrlabel进行标注,并且显示没有问题;
3.训练:
采用configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_cml.yml,并修改Backbone: name: PPLCNetV3 det: true,cal_metric_during_train: false,
然后训练最后1个epoch,loss为0,eval acc为0(是因为设置了cal_metric_during_train: false的原因么?要不报错)
4.模型导出
python tools/export_model.py -c configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_cml.yml -o Global.pretrained_model="./output/ch_PP-OCRv4/best_accuracy" Global.save_inference_dir="./output/det_db_inference/"
导出的是3个文件夹 student、student2、teacher,这3个我都试了,文本检测为空。

导出时出现:
image

请问这个是配置文件出现问题了么?

@UserWangZz
Copy link
Collaborator

https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_det_train.tar
configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml
尝试这个

@gengyanlei
Copy link
Author

@UserWangZz 谢谢
我一开始看这个链接也是对应的ch_PP-OCRv4_det_cml.yml呢,它也对应student.yml呢
image

@UserWangZz
Copy link
Collaborator

问题解决了吗?

@gengyanlei
Copy link
Author

@UserWangZz
正在训练中,loss啥的都正常了。待测试

@UserWangZz
Copy link
Collaborator

你好,请问还有问题吗

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

No branches or pull requests

3 participants