search

yinboc / liif

Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)
https://yinboc.github.io/liif/
BSD 3-Clause "New" or "Revised" License
1.26k stars 145 forks source link

About the loss function in the code #19

Closed destructive-observer closed 3 years ago

destructive-observer commented 3 years ago

Thanks a lot for your excellent work.But i get a confusion in the code.The loss function is L1-loss in your work, but i can not find the loss for the edsr-baseline.Is it only a L1-Loss to train for your mlp-layers and your edsr-baseline as a whole networks? Forward your reply ,thank you.

yinboc commented 3 years ago

Thanks for your interest. Yes, there is only a L1 loss between the final output and ground-truth.