search

PaddlePaddle / PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
Apache License 2.0
40.31k stars 7.46k forks source link

【论文复现】OCR识别模型Parseq #10452

Closed shiyutang closed 5 months ago

shiyutang commented 11 months ago

背景

经过需求征集https://github.com/PaddlePaddle/PaddleOCR/issues/10334 和每周技术研讨会 https://github.com/PaddlePaddle/PaddleOCR/issues/10223 讨论，我们确定了【论文复现】OCR识别模型Parseq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：https://github.com/baudm/parseq
  2. 结合论文复现指南和新增模型指南，进行前反向对齐等操作，达到论文Table.6中的指标。
  3. 参考PR提交规范提交代码PR到ppocr中。
github-actions[bot] commented 6 months ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.