Replies: 3 comments 5 replies
-
能麻烦给一下这部分的原图吗?内部有一些参数,但是未对外提供参数,可能需要依靠源码调整,我可以先试试是否可行 |
Beta Was this translation helpful? Give feedback.
1 reply
-
emmm,大概知道为什么了,是代码执行时为了找到更多的横竖线和识别框,进行了闭合运算还有线延长,我可以加参数让大家自己决定 |
Beta Was this translation helpful? Give feedback.
4 replies
-
已经合并代码了哈,版本也更新了,可能清华的源同步需要等等,可以参考参数进行设置了,本场景,建议把增强线框搜索的参数都设置为Fasle |
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
-
竖着的合并单元格会被识别成了几个单独的格子,里面的文本也被拆分到不同格子了,如下图所示。
这种情况除了对模型迁移训练,还有其它调整方法吗
Beta Was this translation helpful? Give feedback.
All reactions