JingyunLiang / FKP

Official PyTorch code for Flow-based Kernel Prior with Application to Blind Super-Resolution (FKP, CVPR2021)

Home Page:https://arxiv.org/abs/2103.15977

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to test on my own images?

ningbende opened this issue · comments


hi Jingyun,
Thanks for your work. There are too many test code in the project which make me confuesd.
I just want to test on my own image, what should do ?
Thanks again.

If you want to test on synthesized images, please follow the README.md. Taking Set5 as an example, please first generate (HR, LR, kernel) triplets by python prepare_dataset.py --model DIPFKP --sf 2 --dataset Set5 and then test the model by python main.py --SR --sf 2 --dataset Set5. You may need to organize your images as ./data/datasets/Set5/HR/baby.png.

If you want to test on real images without ground-truth kernels, just put your images in ./data/datasets/Set5/DIPFKP_lr_x4 and run python main.py --SR --sf 4 --dataset Set5 --real.


Thanks a lot!

ezoic increase your site revenue