github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-07 13:32:09 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

SAE: new options face_style_power, bg_style_power instead of style_power. Zero - means dont use style.

Browse source 
SAE: new option 'lighter_encoder'.
Now model settings can be overrided by pressing enter in 2 seconds while model loading (works on Windows).
Removed all MultiGPU models, because keras multi_gpu in fact doesn't work.
This commit is contained in:
iperov 2019-01-10 18:28:12 +04:00
parent c3f175862a
commit 48d0123f0b
9 changed files with 158 additions and 139 deletions
Download patch file Download diff file Expand all files Collapse all files

3
models/Model_H64/Model.py
View file

@ -33,9 +33,6 @@ class Model(ModelBase):
self.ae = Model([input_src_bgr,input_src_mask,input_dst_bgr,input_dst_mask], [rec_src_bgr, rec_src_mask, rec_dst_bgr, rec_dst_mask] )
if self.is_training_mode:
self.ae, = self.to_multi_gpu_model_if_possible ( [self.ae,] )
self.ae.compile(optimizer=Adam(lr=5e-5, beta_1=0.5, beta_2=0.999),
loss=[ DSSIMMaskLoss([input_src_mask]), 'mae', DSSIMMaskLoss([input_dst_mask]), 'mae' ] )