search

The-Learning-And-Vision-Atelier-LAVA / DASR

[CVPR 2021] Unsupervised Degradation Representation Learning for Blind Super-Resolution
MIT License
388 stars 50 forks source link

How to test on a real-world image? #7

Open Fangzhenxuan opened 3 years ago

Fangzhenxuan commented 3 years ago

Thank you for sharing your excellent work!! In your test code, it seens we only need to provide benchmark HR test images, but how could I test on a real-world image that dont have label ?

LongguangWang commented 3 years ago

Hi @Fangzhenxuan, thanks for your interest in our work. To super-resolve a real-world image, you can revise trainer.py to remove the codes for LR image generation (Line 149-151) and directly feed the real-world image to our model.

ymtupup commented 3 years ago

you solve this problem？ how to do this

Yaoxingtian commented 3 years ago

Hi @Fangzhenxuan, thanks for your interest in our work. To super-resolve a real-world image, you can revise trainer.py to remove the codes for LR image generation (Line 149-151) and directly feed the real-world image to our model. Do you mean we need to retrain the model, so that we can test a real-word image ?

LongguangWang commented 3 years ago

Hi @Yaoxingtian, we have provided a quick_test API and you can try it on a real-world image.

huacongke commented 1 year ago

have you solved this problem?how to do this