Update url.md

README.md

@@ -73,14 +73,14 @@ python setup.py develop
 - 训练：
 [ImageNet dataset](https://image-net.org/challenges/LSVRC/2012/2012-downloads.php)
 
-[DIV2K Train Data (HR images)](http://113.200.138.88:18080/aidatasets/project-dependency/div2k/-/blob/master/DIV2K_train_HR.zip)
+[DIV2K Train Data (HR images)](http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip)
 
-[Flickr2K](http://113.200.138.88:18080/aidatasets/project-dependency/flickr2k/-/blob/master/Flickr2K.tar)
+[Flickr2K](http://cv.snu.ac.kr/research/EDSR/Flickr2K.tar)
 
 > 训练数据处理请参考[BasicSR](https://github.com/XPixelGroup/BasicSR/blob/master/docs/DatasetPreparation.md)
 
 - 测试：
-[Classical SR Testing](http://113.200.138.88:18080/aidatasets/project-dependency/classical-sr)
+`Classical SR Testing`
 
 数据准备具体步骤如下：
 
@@ -192,7 +192,7 @@ bash val.sh
 交通,公安,制造
 
 ## 预训练权重
-预训练模型下载地址：[SCNet-AIModels](http://113.200.138.88:18080/aimodels/findsource-dependency/hat_pytorch)
+预训练模型下载地址：[pretrained models](https://drive.google.com/drive/folders/1HpmReFfoUqUbnAOQ7rvOeNU3uf_m69w0)
 
 ## 源码仓库及问题反馈
 - https://developer.hpccube.com/codes/modelzoo/hat_pytorch