zwx8981 / LIQE

[CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
MIT License
178 stars 10 forks source link

How to generate degradations?[FileNotFound] #11

Closed RobinY99 closed 10 months ago

RobinY99 commented 10 months ago

Thanks for your sharing!

After " python train_unique_clip_weight.py ", I got FileNotFoundError: [Errno 2] No such file or directory: './IQA_Database/databaserelease2/fastfading/img10.bmp'. Actually, there is no folder named fastfading. I think there should be some codes to generate several degraded versions and input them into such a folder.

Waiting for your reply!

zwx8981 commented 10 months ago

Hi @RobinY99 , thanks for your interest in our work.

You can find the LIVE dataset here, where all distorted images have been included.

https://live.ece.utexas.edu/research/Quality/subjective.htm

RobinY99 commented 10 months ago

Thanks for your reply!