github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-08-19 13:09:56 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #143 from faceshiftlabs/fix/gan-tensorshape-error

Browse source 
Fix/gan tensorshape error
This commit is contained in:
Jeremy Hummel 2021-05-08 14:06:29 -07:00 • committed by GitHub
commit eb0477f0f8
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 7 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
CHANGELOG.md
View file

@ -4,6 +4,10 @@ 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).
## [1.6.2] - 2021-05-08
### Fixed
- Fixed bug with GAN smoothing/noisy labels with certain versions of Tensorflow
## [1.6.1] - 2021-05-04
### Fixed
- Fixed bug when `fs-aug` used on model with same resolution as dataset
@ -88,6 +92,7 @@ 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))
[1.6.2]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.6.1...v1.6.2
[1.6.1]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.6.0...v1.6.1
[1.6.0]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.5.1...v1.6.0
[1.5.1]: https://github.com/faceshiftlabs/DeepFaceLab/compare/v1.5.0...v1.5.1

4
models/Model_SAEHD/Model.py
View file

@ -145,7 +145,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
default_gan_patch_size = self.options['gan_patch_size'] = self.load_or_def_option('gan_patch_size', self.options['resolution'] // 8)
default_gan_dims = self.options['gan_dims'] = self.load_or_def_option('gan_dims', 16)
default_gan_smoothing = self.options['gan_smoothing'] = self.load_or_def_option('gan_smoothing', 0.1)
default_gan_noise = self.options['gan_noise'] = self.load_or_def_option('gan_noise', 0.05)
default_gan_noise = self.options['gan_noise'] = self.load_or_def_option('gan_noise', 0.0)
if self.is_first_run() or ask_override:
self.options['models_opt_on_gpu'] = io.input_bool ("Place models and optimizer on GPU", default_models_opt_on_gpu, help_message="When you train on one GPU, by default model and optimizer weights are placed on GPU to accelerate the process. You can place they on CPU to free up extra VRAM, thus set bigger dimensions.")
@ -580,7 +580,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
x = tf.cast(x, tf.float32)
x = tf.math.scalar_mul(1-smoothing, x)
# x = x + (smoothing/num_labels)
x = tf.reshape(x, (self.batch_size,) + tensor.shape[1:])
x = tf.reshape(x, (self.batch_size,) + tuple(tensor.get_shape().as_list()[1:]))
return x
smoothing = self.options['gan_smoothing']