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

求助:ppstructure和ocr是否支持batch推理?请给个样例 #11884

Closed
charliedream1 opened this issue Apr 7, 2024 · 4 comments
Closed
Assignees
Labels
Code PR is needed This issue could inspire a code PR status/close

Comments

@charliedream1
Copy link

背景

经过需求征集#10334 和每周技术研讨会 #10223 讨论,我们确定了XXXX任务。

解决步骤

  1. 根据开源代码进行网络结构、评估指标转换。代码链接:XXXX
  2. 结合论文复现指南,进行前反向对齐等操作,达到论文Table.1中的指标。
  3. 参考PR提交规范提交代码PR到ppocr中。
@charliedream1 charliedream1 added the Code PR is needed This issue could inspire a code PR label Apr 7, 2024
@gengyanlei
Copy link

@charliedream1
Copy link
Author

我看到了。

Q: 为什么PaddleOCR检测预测是只支持一张图片测试?即test_batch_size_per_card=1
A:测试的时候,对图像等比例缩放,最长边960,不同图像等比例缩放后长宽不一致,无法组成batch,所以设置为test_batch_size为1。

那我提前统一把图片处理成同样的大小,然后batch推理。有样例代码吗?还是需要自己做比较多的改动?

@TingquanGao
Copy link
Collaborator

没有参考代码,我们也不推荐这样使用,对预测效果影响较大。

@charliedream1
Copy link
Author

charliedream1 commented Apr 11, 2024 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Code PR is needed This issue could inspire a code PR status/close
Projects
None yet
Development

No branches or pull requests

5 participants