-
Notifications
You must be signed in to change notification settings - Fork 21
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to generate seg_label file? #13
Comments
同问,seg_label文件夹下的pkl是如何生成的呢 |
需要有cell box对应的label,然后用cell box的边生成seg label,seg_label指导训练思路和意图类似《Deep Splitting and Merging for Table Structure Decomposition》,TGRNet是一片水文,效果很挫的,推荐尝试下split-merge方式(庖丁用的这种思路),无线表格效果不错,有线差了点 |
好的,感谢回复 |
@xb012 Have you solved the problem? Neither have I. Thank you |
@BurgerBurgerBurger 还是不太懂seg_label的pkl怎么生成的,请问你解决了吗 |
请问为什么无线表效果会比有线表好?SplitMerge方法直观上看应该是有线表效果比较好吧~ |
@June-Li ,请问SPLERGE算法您有成功复现吗?github上有人开源了但是训练数据集采用的是ICDAR2013,表格数量还是太小了,我想用别的大数据集比如tablebank去重新训练,但是不知道该如何转化数据集格式,SPLERGE所用数据集里有一个起始行起始列终止行终止列的数据不知道该怎么生成。 |
请问这里的cell bbox是包含空白区域的那种align cell box呢,还是说仅包围文本的text region鸭 |
I want to use my dataset to train TGRNet model. My dataset contains spatial and logical location, so I want to know how to generate seg_label file.
The text was updated successfully, but these errors were encountered: