github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-08-20 05:23:22 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #139 from faceshiftlabs/fix/ms-ssim-version

Browse source 
Fix/ms ssim version
This commit is contained in:
Jeremy Hummel 2021-04-23 23:11:08 -07:00 • committed by GitHub
commit f0a38bb995
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

8
CHANGELOG.md
View file

@ -4,9 +4,9 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
### In Progress
- [Freezeable layers (encoder/decoder/etc.)](https://github.com/faceshiftlabs/DeepFaceLab/tree/feature/freezable-weights)
## [1.5.1] - 2020-04-23
### Fixed
- Fixes bug with MS-SSIM when using a version of tensorflow < 1.14
## [1.5.0] - 2020-03-29
### Changed
@ -80,7 +80,7 @@ This should help with rough areas directly next to the mask
- 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))
[Unreleased]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.5.0...HEAD
[1.5.1]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.5.0...v1.5.1
[1.5.0]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.4.2...v1.5.0
[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

6
core/leras/layers/MsSsim.py
View file

@ -21,7 +21,11 @@ class MsSsim(nn.LayerBase):
y_true_t = tf.transpose(tf.cast(y_true, tf.float32), [0, 2, 3, 1])
y_pred_t = tf.transpose(tf.cast(y_pred, tf.float32), [0, 2, 3, 1])
ms_ssim_val = tf.image.ssim_multiscale(y_true_t, y_pred_t, max_val, power_factors=self.power_factors, filter_size=self.kernel_size)
if tf.__version__ >= "1.14":
ms_ssim_val = tf.image.ssim_multiscale(y_true_t, y_pred_t, max_val, power_factors=self.power_factors, filter_size=self.kernel_size)
else:
ms_ssim_val = tf.image.ssim_multiscale(y_true_t, y_pred_t, max_val, power_factors=self.power_factors)
# ssim_multiscale returns values in range [0, 1] (where 1 is completely identical)
# subtract from 1 to get loss
return 1.0 - ms_ssim_val