Closed PlanesCrossing closed 5 years ago
Thanks so much for your implementation.
However I noticed that there is no annealed L0 loss implemented in this current version. Do you plan to update to include this in the future? Especially I notice that L0 showed much better performances in some of the tasks from the original paper.
Thank you for your suggestion. I'll try later.
Random-valued impulse noise model and L0 loss were now implemented!
This is great, thanks so much!
Thanks so much for your implementation.
However I noticed that there is no annealed L0 loss implemented in this current version. Do you plan to update to include this in the future? Especially I notice that L0 showed much better performances in some of the tasks from the original paper.