This website requires JavaScript.
Explore
Help
Sign In
CalvinBackup
/
iperov-DeepFaceLab
Watch
1
Star
0
Fork
0
You've already forked iperov-DeepFaceLab
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
f044c99ddc158cd23d090826f22957bdffd0ee06
iperov-DeepFaceLab
/
core
/
leras
/
models
T
History
iperov
35877dbfd7
AMP, SAEHD: added option use_fp16: Increases training/inference speed, reduces model size. Model may crash. Enable it after 1-5k iters.
...
AMP: removed lr_dropout, now it is enabled by default;
2021-07-14 23:03:54 +04:00
..
__init__.py
New script:
2020-03-30 14:00:40 +04:00
CodeDiscriminator.py
global refactoring and fixes,
2020-03-13 08:09:00 +04:00
ModelBase.py
fix depth_to_space for tf2.4.0. Removing compute_output_shape in leras, because it uses CPU device, which does not support all ops.
2020-12-11 11:28:33 +04:00
PatchDiscriminator.py
AMP, SAEHD: added option use_fp16: Increases training/inference speed, reduces model size. Model may crash. Enable it after 1-5k iters.
2021-07-14 23:03:54 +04:00
XSeg.py
XSeg model has been changed to work better with large amount of various faces, thus you should retrain existing xseg model.
2021-05-12 13:28:48 +04:00