From 7fc4772e5f2cfc6a491703174690060427968c19 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=88=B5=E4=B8=BB?= <haiduohaiduo@outlook.com>
Date: Sat, 9 Jul 2022 17:32:00 +0800
Subject: [PATCH] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 3de3409..0064301 100644
--- a/README.md
+++ b/README.md
@@ -5,7 +5,8 @@ A code reproduction of VITA.
 
 1. see  [Mask2Former](https://github.com/facebookresearch/Mask2Former/edit/main/INSTALL.md)
 2. see  [IFC](https://github.com/sukjunhwang/IFC#steps)
-3. the Datasets need place in up the root of detertrons that as follows : [catalogue_desc](https://github.com/haiduo/VITA_reproduction/blob/main/catalogue.png)
+3. The Datasets need to be placed up the root of detertrons as follows ：[catalogue_desc](https://github.com/haiduo/VITA_reproduction/blob/main/catalogue.png)
+4. You need to add [YouTubeVIS 2019 model weight of Mask2Former about Video Instance Segmentation](https://dl.fbaipublicfiles.com/maskformer/video_mask2former/ytvis_2019/video_maskformer2_R50_bs16_8ep/model_final_34112b.pkl) to weights folder as for as a pre-training model.
 
 # Note
 - Based on **detectron2**.