Open Salmashi opened 3 years ago
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 @LongguangWang ,why did you extract two patches from each image?
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.
The resolution of images in DF2K is relatively high. May I ask if you need to crop to a certain resolution before training?