DASR
DASR copied to clipboard
Published
20 hours ago •
The-Learning-And-Vision-Atelier-LAVA
The-Learning-And-Vision-Atelier-LAVA
a question about train
The resolution of images in DF2K is relatively high. May I ask if you need to crop to a certain resolution before training?
Hi @Salmashi, thanks for your interest in our work. We do not need to crop the HR images before training. Patches will be cropped online in the dataloader (https://github.com/LongguangWang/DASR/blob/main/data/multiscalesrdata.py#L157)
Hi @jiahong-fu, we extract two patches from one image to construct positive pairs (with the same degradation) for contrastive learning, as illustrated in Fig. 1.