layout-model-training icon indicating copy to clipboard operation
layout-model-training copied to clipboard

Need suggestion while label mapping

Open SAIVENKATARAJU opened this issue 4 years ago • 2 comments

Hi, I am currently fine tuning layout parser on my custom dataset. I am using pubLayNet/faster_rcnn_R_50_FPN_3x as my base model but according to this model output label set is something like this. {0: "Text", 1: "Title", 2: "List", 3: "Table", 4: "Figure"}. but in my original PDF I just want to use "Title", "Section", "Paragraph", "ListItem", PageNumber""Table". my question is : what should be the order of the label mapping. Also, with use of pre-trained model its pretty much detecting tables in custom data and I Just don't want to ruin it. can you please suggest me how should I Move along?.

SAIVENKATARAJU avatar Nov 19 '21 17:11 SAIVENKATARAJU

Hello. Did you find an solution for this problem? I want to fine tuning layout parsor my custom dataset like you, and the category of label and the number of label of my dataset would be slightly different from Layout-Parser. If you found the solution, can you tell me how? Thank you!

kyle-bong avatar May 03 '22 06:05 kyle-bong