MRAE performance

[Fern-Luiz]

Hello, while the paper shows MRAE 0.06+ on Real world NTIRE 2020, I use AWAN+ algorithm to test the validation set (provided by competition in google drive)on real word but get MRAE 0.1+. Do you have any different tricks that not published in your paper?

[Deep-imagelab]

You can download the pretrain models from the link- https://drive.google.com/drive/folders/1cn3q33tTgPaaAlYiGQ20fycxgo9m_F4s?usp=sharing

[Fern-Luiz]

You can download the pretrain models from the link- https://drive.google.com/drive/folders/1cn3q33tTgPaaAlYiGQ20fycxgo9m_F4s?usp=sharing

I do used the pretrain models from link you provided, but got MRAE 0.1+. Can you show the final validation result (.mat files)from AWAN+ of your team?

[Deep-imagelab]

You can download the pretrain models from the link- https://drive.google.com/drive/folders/1cn3q33tTgPaaAlYiGQ20fycxgo9m_F4s?usp=sharing

I do used the pretrain models from link you provided, but got MRAE 0.1+. Can you show the final validation result (.mat files)from AWAN+ of your team?

We have corrected this link.You can try again.The final verification set result is being uploaded to Google Drive, the link will be shared with you later.

[Fern-Luiz]

Thank you, look forword to your link!

[Deep-imagelab]

Thank you, look forword to your link!

We have uploaded the corresponding results, please check carefully the README.md in the direction "AWAN_RealWorld\test" .