search

Alan-xw / RealSR

[Unofficial implementation] Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model (ICCV 2019)
81 stars 11 forks source link

training for x4 super resolution #6

Open NasrinR791 opened 4 years ago

NasrinR791 commented 4 years ago

Dear @Alan-xw , thank you for your code. I want to train LP-KPN model for superresolution task in which the input lr images are 4 times smaller than GT. I wonder which part of the model I should change. Could you please give me any advice on this?

Alan-xw commented 4 years ago

Hi, you can import torch.nn.functional as F module and use F.interpolate() function to upscale image first.

yjt9299 commented 3 years ago

Dear @Alan-xw , thank you for your code. I want to train LP-KPN model for superresolution task in which the input lr images are 4 times smaller than GT. I wonder which part of the model I should change. Could you please give me any advice on this?

I want to ask, have you reproduced successfully with this code? Thank u