如何训练一个性能比得上ch_PP-OCRv4_rec_server_infer的数字识别模型? #12492
Unanswered
1191658517
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
十分感谢paddle的无私开源!
我想训练一个只识别价签中 0 1 2 3 4 5 6 7 8 9 . 这十一个字符的的识别模型。但是微调训练出来的发现比ch_PP-OCRv4_rec_server_infer的效果还差一些。可ch_PP-OCRv4_rec_server_infer由于字典过全又有一个无法避免的问题:在比较模糊的情况下容易把 11 识别成 几、n、m、h、II 这样的字符。
我该如何在保持ch_PP-OCRv4_rec_server_infer的模型能力的情况下,让字典变成我想要的某部分子集呢?是需要做蒸馏吗?
若能解答,万分感谢!
Beta Was this translation helpful? Give feedback.
All reactions