search

Layout-Parser / layout-parser

A Unified Toolkit for Deep Learning Based Document Image Analysis
https://layout-parser.github.io/
Apache License 2.0
4.64k stars 449 forks source link

Might PubLayNet label mapping be incorrect? #178

Open opyate opened 1 year ago

opyate commented 1 year ago

Hello, thanks for this very useful toolkit.

According to the official PubLayNet docs, they had this mapping:

Category id Label
0 Background
1 Text
2 Title
3 List
4 Table
5 Figure

But in the model zoo docs, you specify this mapping:

{0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"}

Please advise on the discrepancy. Kind regards!