search

cuiziteng / Illumination-Adaptive-Transformer

🌕 [BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-processing.
Apache License 2.0
459 stars 43 forks source link

Evaluation pretrain model on LOL-V1 dataset #9

Closed minhthien2206 closed 2 years ago

minhthien2206 commented 2 years ago

Hi authors, I try to run the code to evaluate the model on the LOL-V1 dataset. I follow as your command: "python evaluation_lol_v1.py --img_val_path Your_Path/eval15/low/". However, I can not get the results. The terminal show as: image Could you please show me how to fix and obtain the results?

cuiziteng commented 2 years ago

Hello! It seem like you haven't correct load the images in LOL-V1 dataset , you need to first download LOL-V1 dataset from the this website: https://daooshee.github.io/BMVC2018website/, and then map the dataset as the format:

image

Note that Your_Path is not a certain path, it is the path you place LOL-V1 dataset, any question else please drop here~

minhthien2206 commented 2 years ago

Hi authors, I already formatted it like your guidance. image And inside the code, I also change the link as follows: image The error still happens: image

cuiziteng commented 2 years ago

Hello, don't forget to add a '/' in the end of the path, change it to './datasets/LOL_v1/eval15/low/' and try again~

minhthien2206 commented 2 years ago

Yes, thanks for your answer. I already fixed the error.