Layout-Parser / layout-parser

A Unified Toolkit for Deep Learning Based Document Image Analysis
https://layout-parser.github.io/
Apache License 2.0
4.82k stars 464 forks source link

Including VGT pretrain model #204

Open naarkhoo opened 8 months ago

naarkhoo commented 8 months ago

Motivation Vision Grid Transformer for Document Layout Analysis should outstanding performance w.r.t to https://paperswithcode.com/paper/vision-grid-transformer-for-document-layout (above 95% on PubLayNet.

Related resources https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/VGT

Additional context NA