github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-08-20 13:33:24 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #135 from faceshiftlabs/fix/background-power-bug

Browse source 
Fix/background power bug
This commit is contained in:
Jeremy Hummel 2021-03-26 06:06:59 -07:00 • committed by GitHub
commit 775f0e739d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 8 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

9
CHANGELOG.md
View file

@ -8,7 +8,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### In Progress ### In Progress
- [Freezeable layers (encoder/decoder/etc.)](https://github.com/faceshiftlabs/DeepFaceLab/tree/feature/freezable-weights) - [Freezeable layers (encoder/decoder/etc.)](https://github.com/faceshiftlabs/DeepFaceLab/tree/feature/freezable-weights)
## [1.4.1] - 2020-03-24 ## [1.4.2] - 2020-03-26
### Fixed
- Fixes bug in background power with MS-SSIM, that misattributed loss from dst to src
## [1.4.1] - 2020-03-25
### Fixed ### Fixed
- When both Background Power and MS-SSIM were enabled, the src and dst losses were being overwritten with the - When both Background Power and MS-SSIM were enabled, the src and dst losses were being overwritten with the
"background power" losses. Fixed so "background power" losses are properly added with the total losses. "background power" losses. Fixed so "background power" losses are properly added with the total losses.
@ -69,7 +73,8 @@ This should help with rough areas directly next to the mask
- Reset stale master branch to [seranus/DeepFaceLab](https://github.com/seranus/DeepFaceLab), - Reset stale master branch to [seranus/DeepFaceLab](https://github.com/seranus/DeepFaceLab),
21 commits ahead of [iperov/DeepFaceLab](https://github.com/iperov/DeepFaceLab) ([compare](https://github.com/iperov/DeepFaceLab/compare/4818183...seranus:3f5ae05)) 21 commits ahead of [iperov/DeepFaceLab](https://github.com/iperov/DeepFaceLab) ([compare](https://github.com/iperov/DeepFaceLab/compare/4818183...seranus:3f5ae05))
[Unreleased]: https://github.com/olivierlacan/keep-a-changelog/compare/v1.4.1...HEAD [Unreleased]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.4.2...HEAD
[1.4.2]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.4.1...v1.4.2
[1.4.1]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.4.0...v1.4.1 [1.4.1]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.4.0...v1.4.1
[1.4.0]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.3.0...v1.4.0 [1.4.0]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.3.0...v1.4.0
[1.3.0]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.2.1...v1.3.0 [1.3.0]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.2.1...v1.3.0

2
models/Model_SAEHD/Model.py
View file

@ -518,7 +518,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
if self.options['background_power'] > 0: if self.options['background_power'] > 0:
bg_factor = self.options['background_power'] bg_factor = self.options['background_power']
if self.options['ms_ssim_loss']: if self.options['ms_ssim_loss']:
gpu_src_loss += bg_factor * 10 * nn.MsSsim(resolution)(gpu_target_dst, gpu_pred_dst_dst, max_val=1.0) gpu_dst_loss += bg_factor * 10 * nn.MsSsim(resolution)(gpu_target_dst, gpu_pred_dst_dst, max_val=1.0)
else: else:
if resolution < 256: if resolution < 256:
gpu_dst_loss += bg_factor * tf.reduce_mean ( 10*nn.dssim(gpu_target_dst, gpu_pred_dst_dst, max_val=1.0, filter_size=int(resolution/11.6)), axis=[1]) gpu_dst_loss += bg_factor * tf.reduce_mean ( 10*nn.dssim(gpu_target_dst, gpu_pred_dst_dst, max_val=1.0, filter_size=int(resolution/11.6)), axis=[1])