You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am hoping you might open-source the log files you have from training. Maybe the training and validation loss as a function of epoch
(and/or batch) with an estimate of the runtime?
The text was updated successfully, but these errors were encountered:
Our TLC is a test-time method that can be applied to already trained models. In other words, TLC is decoupled from the training so that you can use the training process from original papers and use TLC only at test-time.
In this repo, we applied our TLC to public available trained models (checkpoints) and we did not train any of them. For the training log, you may ask for the original author of model's paper: HINet, MPRNet, Restormer.
Thank you for your awesome code!
I am hoping you might open-source the log files you have from training. Maybe the training and validation loss as a function of epoch
(and/or batch) with an estimate of the runtime?
The text was updated successfully, but these errors were encountered: