Skip to content
This repository has been archived by the owner on Oct 7, 2024. It is now read-only.

training loss weight for different scale depth prediction #22

Open
daisily727 opened this issue Jul 17, 2020 · 1 comment
Open

training loss weight for different scale depth prediction #22

daisily727 opened this issue Jul 17, 2020 · 1 comment

Comments

@daisily727
Copy link

the results of my network is quite blur. I feel it is about the loss.

  1. Can I know if you used multi-scale graidient loss? I saw the mega depth paper used 4 scales
  2. Can I know your weight setting for the loss computation on depth prediction at different resolutions, i.e. prediction1, prediction2, and prediction3 in your model. did you used the same weight of those three?

Many thanks!

@FilippoAleotti
Copy link
Owner

Hi,
Yes, I used multi-scale gradient loss, with weights of 0.5, 0.25 and 0.125 for the full, half and quarter resolution predictions respectively. However, lower scale predictions are upsampled to fullres before the overall loss computation.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants