Closed lovecambi closed 2 years ago
Hi Sorry for late reply
No, there is no reason. L1 is only applied to the known part of the image and to the best of our knowledge, does not affect training. It is there just for historical reasons. You can turn L1 loss off altogether and everything should be fine
For the function
masked_l1_loss
(https://github.com/saic-mdal/lama/blob/main/saicinpainting/training/losses/feature_matching.py#L13), I foundweight_known=10
andweight_missing=0
in all config yaml files, so the masked_l1_loss won't calculate the difference on masked region. This seems counter-intuitive. Can you explain the reason?