PaddleOCR icon indicating copy to clipboard operation
PaddleOCR copied to clipboard

想问一下paddlelabel默认的英文模型的训练模型有吗?想拿来作为预训练模型

Open chenshanhuo opened this issue 2 years ago • 4 comments

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:

chenshanhuo avatar Aug 07 '22 16:08 chenshanhuo

有的:https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.5/doc/doc_ch/models_list.md#22-%E8%8B%B1%E6%96%87%E8%AF%86%E5%88%AB%E6%A8%A1%E5%9E%8B image

MissPenguin avatar Aug 08 '22 12:08 MissPenguin

有的:https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.5/doc/doc_ch/models_list.md#22-%E8%8B%B1%E6%96%87%E8%AF%86%E5%88%AB%E6%A8%A1%E5%9E%8B image

请问paddlelabel2.3.0.2的那个默认的英文检测模型有可用于训练的模型吗?如果有的话,有不是蒸馏的吗?

chenshanhuo avatar Aug 09 '22 07:08 chenshanhuo

为什么要不是蒸馏的呢,如果是想用学生模型的参数,可以参考文档进行提取:https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/knowledge_distillation.md#225-%E6%A3%80%E6%B5%8B%E8%92%B8%E9%A6%8F%E6%A8%A1%E5%9E%8Bfinetune

MissPenguin avatar Aug 10 '22 07:08 MissPenguin

为什么要不是蒸馏的呢,如果是想用学生模型的参数,可以参考文档进行提取:https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/knowledge_distillation.md#225-%E6%A3%80%E6%B5%8B%E8%92%B8%E9%A6%8F%E6%A8%A1%E5%9E%8Bfinetune

数据集只有80张,请问适合用蒸馏吗

chenshanhuo avatar Aug 10 '22 07:08 chenshanhuo

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.

github-actions[bot] avatar Jul 07 '23 08:07 github-actions[bot]