From 51876d7212e2f97f5b2eacfce050b2843c87997e Mon Sep 17 00:00:00 2001 From: WeiHaoran <50487563+Ucas-HaoranWei@users.noreply.github.com> Date: Thu, 12 Sep 2024 07:06:31 +0800 Subject: [PATCH] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 479c01c..90ccf2c 100644 --- a/README.md +++ b/README.md @@ -104,6 +104,7 @@ The rendering results can be found in /results/demo.html. Please open the demo.h ## Train +0. Train sample can be seen in [here](https://github.com/Ucas-HaoranWei/GOT-OCR2.0/blob/main/assets/train_sample.jpg). Note that the '\' in the 'conversations'-'human'-'value' is necessary! 1. This codebase only supports post-training (stage-2/stage-3) upon our GOT weights. 2. If you want train from stage-1 described in our paper, you need this [repo](https://github.com/Ucas-HaoranWei/Vary-tiny-600k).