github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-08-22 06:23:20 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

_

Browse source
This commit is contained in:
iperov 2019-04-24 00:49:07 +04:00
commit c66a1d87ef
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
models/Model_SAE/Model.py
View file

@ -265,7 +265,7 @@ class SAEModel(ModelBase):
src_dst_mask_loss_train_weights = self.encoder.trainable_weights + self.decoder_srcm.trainable_weights + self.decoder_dstm.trainable_weights
if not self.options['pixel_loss']:
src_loss_batch = sum([ ( alpha_rec*K.square( dssim(kernel_size=int(resolution/11.6),max_value=1.0)( target_src_masked_ar_opt[i], pred_src_src_masked_ar_opt[i] ) )) for i in range(len(target_src_masked_ar_opt)) ])
src_loss_batch = sum([ alpha_rec*dssim(kernel_size=int(resolution/11.6),max_value=1.0)( target_src_masked_ar_opt[i], pred_src_src_masked_ar_opt[i]) for i in range(len(target_src_masked_ar_opt)) ])
else:
src_loss_batch = sum([ K.mean ( alpha_rec*K.square( target_src_masked_ar_opt[i] - pred_src_src_masked_ar_opt[i] ), axis=[1,2,3]) for i in range(len(target_src_masked_ar_opt)) ])
@ -279,13 +279,13 @@ class SAEModel(ModelBase):
bg_style_power = self.options['bg_style_power'] / 100.0
if bg_style_power != 0:
if not self.options['pixel_loss']:
bg_loss = K.mean( (alpha_rec*bg_style_power)*K.square(dssim(kernel_size=int(resolution/11.6),max_value=1.0)( psd_target_dst_anti_masked_ar[-1], target_dst_anti_masked_ar[-1] )))
bg_loss = K.mean( (alpha_rec*bg_style_power)*dssim(kernel_size=int(resolution/11.6),max_value=1.0)( psd_target_dst_anti_masked_ar[-1], target_dst_anti_masked_ar[-1] ))
else:
bg_loss = K.mean( (alpha_rec*bg_style_power)*K.square( psd_target_dst_anti_masked_ar[-1] - target_dst_anti_masked_ar[-1] ))
src_loss += bg_loss
if not self.options['pixel_loss']:
dst_loss_batch = sum([ ( alpha_rec*K.square(dssim(kernel_size=int(resolution/11.6),max_value=1.0)( target_dst_masked_ar_opt[i], pred_dst_dst_masked_ar_opt[i] ) )) for i in range(len(target_dst_masked_ar_opt)) ])
dst_loss_batch = sum([ alpha_rec*dssim(kernel_size=int(resolution/11.6),max_value=1.0)(target_dst_masked_ar_opt[i], pred_dst_dst_masked_ar_opt[i]) for i in range(len(target_dst_masked_ar_opt)) ])
else:
dst_loss_batch = sum([ K.mean ( alpha_rec*K.square( target_dst_masked_ar_opt[i] - pred_dst_dst_masked_ar_opt[i] ), axis=[1,2,3]) for i in range(len(target_dst_masked_ar_opt)) ])