1.Multi-Scale Attention Network for Image Super-resolution; Link: https://www.sciencedirect.com/science/article/abs/pii/S1047320321001978?dgcid=coauthor
2.To train the DIV2K dataset,using the following command: python train.py -opt options/train/train_msan.json
3.To test the benchmark datasets,using the following command: python test.py -opt options/test/test_msan.json
4.We have provided four models for x2, x3, x4 and x8, respectively. Experiment results can be downloaded from 链接：https://pan.baidu.com/s/1o3j2vUyINK0UnUYt3KGDzw 提取码：1234