github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-06 21:12:07 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

SAEHD: lr_dropout now as an option, and disabled by default

Browse source
This commit is contained in:
Colombo 2019-12-20 10:39:05 +04:00
parent 64021b9c62
commit cf27558e88
1 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

14
models/Model_SAEHD/Model.py
View file

@ -64,7 +64,10 @@ class SAEHDModel(ModelBase):
default_face_style_power = self.options.get('face_style_power', 0.0) default_face_style_power = self.options.get('face_style_power', 0.0)
default_bg_style_power = self.options.get('bg_style_power', 0.0) default_bg_style_power = self.options.get('bg_style_power', 0.0)
if is_first_run or ask_override: if is_first_run or ask_override:
default_lr_dropout = self.options.get('lr_dropout', False)
self.options['lr_dropout'] = io.input_bool ( f"Use learning rate dropout? (y/n, ?:help skip:{yn_str[default_lr_dropout]} ) : ", default_lr_dropout, help_message="When the face is trained enough, you can enable this option to get extra sharpness for less amount of iterations.")
default_random_warp = self.options.get('random_warp', True) default_random_warp = self.options.get('random_warp', True)
self.options['random_warp'] = io.input_bool (f"Enable random warp of samples? ( y/n, ?:help skip:{yn_str[default_random_warp]}) : ", default_random_warp, help_message="Random warp is required to generalize facial expressions of both faces. When the face is trained enough, you can disable it to get extra sharpness for less amount of iterations.") self.options['random_warp'] = io.input_bool (f"Enable random warp of samples? ( y/n, ?:help skip:{yn_str[default_random_warp]}) : ", default_random_warp, help_message="Random warp is required to generalize facial expressions of both faces. When the face is trained enough, you can disable it to get extra sharpness for less amount of iterations.")
@ -84,8 +87,8 @@ class SAEHDModel(ModelBase):
self.options['clipgrad'] = io.input_bool (f"Enable gradient clipping? (y/n, ?:help skip:{yn_str[default_clipgrad]}) : ", default_clipgrad, help_message="Gradient clipping reduces chance of model collapse, sacrificing speed of training.") self.options['clipgrad'] = io.input_bool (f"Enable gradient clipping? (y/n, ?:help skip:{yn_str[default_clipgrad]}) : ", default_clipgrad, help_message="Gradient clipping reduces chance of model collapse, sacrificing speed of training.")
else: else:
self.options['clipgrad'] = False self.options['clipgrad'] = False
else: else:
self.options['lr_dropout'] = self.options.get('lr_dropout', default_lr_dropout)
self.options['random_warp'] = self.options.get('random_warp', True) self.options['random_warp'] = self.options.get('random_warp', True)
self.options['true_face_training'] = self.options.get('true_face_training', default_true_face_training) self.options['true_face_training'] = self.options.get('true_face_training', default_true_face_training)
self.options['face_style_power'] = self.options.get('face_style_power', default_face_style_power) self.options['face_style_power'] = self.options.get('face_style_power', default_face_style_power)
@ -452,9 +455,10 @@ class SAEHDModel(ModelBase):
psd_target_dst_anti_masked = self.model.pred_src_dst*(1.0 - target_dstm) psd_target_dst_anti_masked = self.model.pred_src_dst*(1.0 - target_dstm)
if self.is_training_mode: if self.is_training_mode:
self.src_dst_opt = RMSprop(lr=5e-5, lr_dropout=0.3, clipnorm=1.0 if self.options['clipgrad'] else 0.0, tf_cpu_mode=self.options['optimizer_mode']-1) lr_dropout = 0.3 if self.options['lr_dropout'] else 0.0
self.src_dst_mask_opt = RMSprop(lr=5e-5, lr_dropout=0.3, clipnorm=1.0 if self.options['clipgrad'] else 0.0, tf_cpu_mode=self.options['optimizer_mode']-1) self.src_dst_opt = RMSprop(lr=5e-5, lr_dropout=lr_dropout, clipnorm=1.0 if self.options['clipgrad'] else 0.0, tf_cpu_mode=self.options['optimizer_mode']-1)
self.D_opt = RMSprop(lr=5e-5, lr_dropout=0.3, clipnorm=1.0 if self.options['clipgrad'] else 0.0, tf_cpu_mode=self.options['optimizer_mode']-1) self.src_dst_mask_opt = RMSprop(lr=5e-5, lr_dropout=lr_dropout, clipnorm=1.0 if self.options['clipgrad'] else 0.0, tf_cpu_mode=self.options['optimizer_mode']-1)
self.D_opt = RMSprop(lr=5e-5, lr_dropout=lr_dropout, clipnorm=1.0 if self.options['clipgrad'] else 0.0, tf_cpu_mode=self.options['optimizer_mode']-1)
src_loss = K.mean ( 10*dssim(kernel_size=int(resolution/11.6),max_value=1.0)( target_src_masked_opt, pred_src_src_masked_opt) ) src_loss = K.mean ( 10*dssim(kernel_size=int(resolution/11.6),max_value=1.0)( target_src_masked_opt, pred_src_src_masked_opt) )
src_loss += K.mean ( 10*K.square( target_src_masked_opt - pred_src_src_masked_opt ) ) src_loss += K.mean ( 10*K.square( target_src_masked_opt - pred_src_src_masked_opt ) )