字典中不存在的字怎么识别 #12456
Unanswered
hezhenname
asked this question in
Q&A
字典中不存在的字怎么识别
#12456
Replies: 3 comments
-
把这个字加到字典里,然后准备包含包含这个字的数据集,重新训练模型 |
Beta Was this translation helpful? Give feedback.
0 replies
-
这个字典有6600+的字符,数据集要怎么准备才合理,需要准备多少张图片的数据,原本能识别的字符也需要被包括吗?因为目前可能就个别字识别错误,其他的识别准确率还是挺高的,担心训练之后原本能识别的字变得不能识别,就是需要保证原本的识别准确率不下降,同时又能识别新加的字符 |
Beta Was this translation helpful? Give feedback.
0 replies
-
理论上就是要重新整你的字典了,你可以在原来的上面增删改,构建一个你觉得合适的字典。毕竟是重新训练,“保证原本的识别准确率不下降”只能说是个没好的愿望,这就是你自己要权衡的问题了,当然最后准确率还是得看你的数据集质量。 |
Beta Was this translation helpful? Give feedback.
0 replies
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.
-
请问如果ppocr_keys_v1.txt字典里面不包含的字,比如“纡”,想要识别的话,需要怎么做
Beta Was this translation helpful? Give feedback.
All reactions