Replies: 7 comments
-
Same problem here, could you please share your .yml and train_data folder structure |
Beta Was this translation helpful? Give feedback.
-
看样子是由于V4文字检测模型配置文件引入的一个问题。 应该是引入了动态shrink ratio(dynamic shrink ratio):在训练中,shrink ratio由固定值调整为动态变化,随着训练epoch的增加,shrink ratio从0.4线性增加到0.6。该策略在PP-OCRv4学生检测模型上,hmean从76.97%提升到78.24%。 - MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
total_epoch: *epoch_num
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
total_epoch: *epoch_num 应该不会影响识别效果? @dhhcj 大佬,你测试过这个模型效果了吗? |
Beta Was this translation helpful? Give feedback.
-
official ch_PP-OCRv4_rec_hgnet.yml, just change the default label_file_list and pretrained_model |
Beta Was this translation helpful? Give feedback.
-
|
Beta Was this translation helpful? Give feedback.
-
emm,训练的时候直接注释掉得了,只要不影响效果就好。 |
Beta Was this translation helpful? Give feedback.
-
你好,请问你有试过动态shrink么,真的有提点么? |
Beta Was this translation helpful? Give feedback.
-
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
我们提供了AceIssueSolver来帮助你解答问题,你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no):
请尽量不要包含图片在问题中/Please try to not include the image in the issue.
这个是V4版本:
旧的V2版本:
并不会出现这个问题
Beta Was this translation helpful? Give feedback.
All reactions