From a09e219605a60ab73914ed92b8bfcdbc3fc12c2e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=EC=98=81=EC=A0=9C=20=EC=9E=84?= <iyj0121@ajou.ac.kr>
Date: Fri, 8 Sep 2023 20:58:28 +0900
Subject: [PATCH] Update README.md

---
 README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.md b/README.md
index 080056a..ed3903d 100755
--- a/README.md
+++ b/README.md
@@ -8,6 +8,7 @@
 
 <img width="712" alt="스크린샷 2023-04-09 오후 1 01 52" src="https://user-images.githubusercontent.com/90498398/236676450-5e7d3073-e2b0-47da-bc13-8187581af0e2.png">
 <img width="298" alt="스크린샷 2023-05-03 오후 8 07 38" src="https://user-images.githubusercontent.com/90498398/236676461-02a1bc78-14c7-4144-852f-4886d3ffae60.png">
+https://github.com/yulunzhang/RCAN/raw/master/Figs/RCAN.PNG
 
 This study aims to restore resolution to improve image quality. The entire framework consists of two models, vdsr and mask-attention. If SR-reconstruction works well using two models, the loss value is low, and if SR-reconstruction does not work well, the loss value is high, so it is a model that focuses on hard samples. This allows us to focus on samples that are difficult to rebuild, and is a kind of ensemble (mining technique that focuses on hard samples) as an opportunity to make more use of local details.
 In addition, this study placed restrictions on convolution using masks when learning models. Through this, when testing the model, it can be effectively applied to reconstruct the image.
-- 
GitLab