github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-05 20:42:11 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

SAEHD: random scale increased to -0.15+0.15. Improved lr_dropout capability to reach lower value of the loss.

Browse source 
When random_warp is off, inter_AB network is no longer trained to keep the face more src-like.

added option Random hue/saturation/light intensity applied to the src face set only at the input of the neural network. Stabilizes color perturbations during face swapping. Reduces the quality of the color transfer by selecting the closest one in the src faceset. Thus the src faceset must be diverse enough. Typical fine value is 0.05.

AMP: random scale increased to -0.15+0.15. Improved lr_dropout capability to reach lower value of the loss.
This commit is contained in:
iperov 2021-10-18 11:03:23 +04:00
parent f71a9e6bbd
commit 71f22957a6
2 changed files with 54 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

31
models/Model_AMP/Model.py
View file

@ -292,20 +292,21 @@ class AMPModel(ModelBase):
if self.is_training: if self.is_training:
# Initialize optimizers # Initialize optimizers
clipnorm = 1.0 if self.options['clipgrad'] else 0.0 clipnorm = 1.0 if self.options['clipgrad'] else 0.0
lr_dropout = 0.3 if self.options['lr_dropout'] in ['y','cpu'] else 1.0 if self.options['lr_dropout'] in ['y','cpu'] and not self.pretrain:
lr_cos = 500
lr_dropout = 0.3
else:
lr_cos = 0
lr_dropout = 1.0
self.G_weights = self.encoder.get_weights() + self.decoder.get_weights() self.G_weights = self.encoder.get_weights() + self.decoder.get_weights()
#if random_warp: self.src_dst_opt = nn.AdaBelief(lr=5e-5, lr_dropout=lr_dropout, lr_cos=lr_cos, clipnorm=clipnorm, name='src_dst_opt')
# self.G_weights += self.inter_src.get_weights() + self.inter_dst.get_weights()
self.src_dst_opt = nn.AdaBelief(lr=5e-5, lr_dropout=lr_dropout, clipnorm=clipnorm, name='src_dst_opt')
self.src_dst_opt.initialize_variables (self.G_weights, vars_on_cpu=optimizer_vars_on_cpu) self.src_dst_opt.initialize_variables (self.G_weights, vars_on_cpu=optimizer_vars_on_cpu)
self.model_filename_list += [ (self.src_dst_opt, 'src_dst_opt.npy') ] self.model_filename_list += [ (self.src_dst_opt, 'src_dst_opt.npy') ]
if gan_power != 0: if gan_power != 0:
self.GAN = nn.UNetPatchDiscriminator(patch_size=self.options['gan_patch_size'], in_ch=input_ch, base_ch=self.options['gan_dims'], name="GAN") self.GAN = nn.UNetPatchDiscriminator(patch_size=self.options['gan_patch_size'], in_ch=input_ch, base_ch=self.options['gan_dims'], name="GAN")
self.GAN_opt = nn.AdaBelief(lr=5e-5, lr_dropout=lr_dropout, clipnorm=clipnorm, name='GAN_opt') self.GAN_opt = nn.AdaBelief(lr=5e-5, lr_dropout=lr_dropout, lr_cos=lr_cos, clipnorm=clipnorm, name='GAN_opt')
self.GAN_opt.initialize_variables ( self.GAN.get_weights(), vars_on_cpu=optimizer_vars_on_cpu) self.GAN_opt.initialize_variables ( self.GAN.get_weights(), vars_on_cpu=optimizer_vars_on_cpu)
self.model_filename_list += [ [self.GAN, 'GAN.npy'], self.model_filename_list += [ [self.GAN, 'GAN.npy'],
[self.GAN_opt, 'GAN_opt.npy'] ] [self.GAN_opt, 'GAN_opt.npy'] ]
@ -391,15 +392,15 @@ class AMPModel(ModelBase):
if blur_out_mask: if blur_out_mask:
sigma = resolution / 128 sigma = resolution / 128
x = nn.gaussian_blur(gpu_target_src*gpu_target_srcm_anti, sigma) x = nn.gaussian_blur(gpu_target_src*gpu_target_srcm_anti, sigma)
y = 1-nn.gaussian_blur(gpu_target_srcm, sigma) y = 1-nn.gaussian_blur(gpu_target_srcm, sigma)
y = tf.where(tf.equal(y, 0), tf.ones_like(y), y) y = tf.where(tf.equal(y, 0), tf.ones_like(y), y)
gpu_target_src = gpu_target_src*gpu_target_srcm + (x/y)*gpu_target_srcm_anti gpu_target_src = gpu_target_src*gpu_target_srcm + (x/y)*gpu_target_srcm_anti
x = nn.gaussian_blur(gpu_target_dst*gpu_target_dstm_anti, sigma) x = nn.gaussian_blur(gpu_target_dst*gpu_target_dstm_anti, sigma)
y = 1-nn.gaussian_blur(gpu_target_dstm, sigma) y = 1-nn.gaussian_blur(gpu_target_dstm, sigma)
y = tf.where(tf.equal(y, 0), tf.ones_like(y), y) y = tf.where(tf.equal(y, 0), tf.ones_like(y), y)
gpu_target_dst = gpu_target_dst*gpu_target_dstm + (x/y)*gpu_target_dstm_anti gpu_target_dst = gpu_target_dst*gpu_target_dstm + (x/y)*gpu_target_dstm_anti
gpu_target_src_masked = gpu_target_src*gpu_target_srcm_blur gpu_target_src_masked = gpu_target_src*gpu_target_srcm_blur
@ -561,7 +562,7 @@ class AMPModel(ModelBase):
self.set_training_data_generators ([ self.set_training_data_generators ([
SampleGeneratorFace(training_data_src_path, random_ct_samples_path=random_ct_samples_path, debug=self.is_debug(), batch_size=self.get_batch_size(), SampleGeneratorFace(training_data_src_path, random_ct_samples_path=random_ct_samples_path, debug=self.is_debug(), batch_size=self.get_batch_size(),
sample_process_options=SampleProcessor.Options(scale_range=[-0.125, 0.125], random_flip=self.random_src_flip), sample_process_options=SampleProcessor.Options(scale_range=[-0.15, 0.15], random_flip=self.random_src_flip),
output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution}, output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution},
@ -571,7 +572,7 @@ class AMPModel(ModelBase):
generators_count=src_generators_count ), generators_count=src_generators_count ),
SampleGeneratorFace(training_data_dst_path, debug=self.is_debug(), batch_size=self.get_batch_size(), SampleGeneratorFace(training_data_dst_path, debug=self.is_debug(), batch_size=self.get_batch_size(),
sample_process_options=SampleProcessor.Options(scale_range=[-0.125, 0.125], random_flip=self.random_dst_flip), sample_process_options=SampleProcessor.Options(scale_range=[-0.15, 0.15], random_flip=self.random_dst_flip),
output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution}, output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':face_type, 'data_format':nn.data_format, 'resolution': resolution},

61
models/Model_SAEHD/Model.py
View file

@ -53,6 +53,7 @@ class SAEHDModel(ModelBase):
default_lr_dropout = self.options['lr_dropout'] = lr_dropout default_lr_dropout = self.options['lr_dropout'] = lr_dropout
default_random_warp = self.options['random_warp'] = self.load_or_def_option('random_warp', True) default_random_warp = self.options['random_warp'] = self.load_or_def_option('random_warp', True)
default_random_hsv_power = self.options['random_hsv_power'] = self.load_or_def_option('random_hsv_power', 0.0)
default_true_face_power = self.options['true_face_power'] = self.load_or_def_option('true_face_power', 0.0) default_true_face_power = self.options['true_face_power'] = self.load_or_def_option('true_face_power', 0.0)
default_face_style_power = self.options['face_style_power'] = self.load_or_def_option('face_style_power', 0.0) default_face_style_power = self.options['face_style_power'] = self.load_or_def_option('face_style_power', 0.0)
default_bg_style_power = self.options['bg_style_power'] = self.load_or_def_option('bg_style_power', 0.0) default_bg_style_power = self.options['bg_style_power'] = self.load_or_def_option('bg_style_power', 0.0)
@ -152,6 +153,8 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
self.options['random_warp'] = io.input_bool ("Enable random warp of samples", 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 and reduce subpixel shake for less amount of iterations.") self.options['random_warp'] = io.input_bool ("Enable random warp of samples", 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 and reduce subpixel shake for less amount of iterations.")
self.options['random_hsv_power'] = np.clip ( io.input_number ("Random hue/saturation/light intensity", default_random_hsv_power, add_info="0.0 .. 0.3", help_message="Random hue/saturation/light intensity applied to the src face set only at the input of the neural network. Stabilizes color perturbations during face swapping. Reduces the quality of the color transfer by selecting the closest one in the src faceset. Thus the src faceset must be diverse enough. Typical fine value is 0.05"), 0.0, 0.3 )
self.options['gan_power'] = np.clip ( io.input_number ("GAN power", default_gan_power, add_info="0.0 .. 5.0", help_message="Forces the neural network to learn small details of the face. Enable it only when the face is trained enough with lr_dropout(on) and random_warp(off), and don't disable. The higher the value, the higher the chances of artifacts. Typical fine value is 0.1"), 0.0, 5.0 ) self.options['gan_power'] = np.clip ( io.input_number ("GAN power", default_gan_power, add_info="0.0 .. 5.0", help_message="Forces the neural network to learn small details of the face. Enable it only when the face is trained enough with lr_dropout(on) and random_warp(off), and don't disable. The higher the value, the higher the chances of artifacts. Typical fine value is 0.1"), 0.0, 5.0 )
if self.options['gan_power'] != 0.0: if self.options['gan_power'] != 0.0:
@ -228,12 +231,14 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
random_warp = False if self.pretrain else self.options['random_warp'] random_warp = False if self.pretrain else self.options['random_warp']
random_src_flip = self.random_src_flip if not self.pretrain else True random_src_flip = self.random_src_flip if not self.pretrain else True
random_dst_flip = self.random_dst_flip if not self.pretrain else True random_dst_flip = self.random_dst_flip if not self.pretrain else True
random_hsv_power = self.options['random_hsv_power'] if not self.pretrain else 0.0
blur_out_mask = self.options['blur_out_mask'] blur_out_mask = self.options['blur_out_mask']
if self.pretrain: if self.pretrain:
self.options_show_override['gan_power'] = 0.0
self.options_show_override['random_warp'] = False
self.options_show_override['lr_dropout'] = 'n' self.options_show_override['lr_dropout'] = 'n'
self.options_show_override['random_warp'] = False
self.options_show_override['gan_power'] = 0.0
self.options_show_override['random_hsv_power'] = 0.0
self.options_show_override['face_style_power'] = 0.0 self.options_show_override['face_style_power'] = 0.0
self.options_show_override['bg_style_power'] = 0.0 self.options_show_override['bg_style_power'] = 0.0
self.options_show_override['uniform_yaw'] = True self.options_show_override['uniform_yaw'] = True
@ -313,26 +318,36 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
# Initialize optimizers # Initialize optimizers
lr=5e-5 lr=5e-5
lr_dropout = 0.3 if self.options['lr_dropout'] in ['y','cpu'] and not self.pretrain else 1.0 if self.options['lr_dropout'] in ['y','cpu'] and not self.pretrain:
lr_cos = 500
lr_dropout = 0.3
else:
lr_cos = 0
lr_dropout = 1.0
OptimizerClass = nn.AdaBelief if adabelief else nn.RMSprop OptimizerClass = nn.AdaBelief if adabelief else nn.RMSprop
clipnorm = 1.0 if self.options['clipgrad'] else 0.0 clipnorm = 1.0 if self.options['clipgrad'] else 0.0
if 'df' in archi_type: if 'df' in archi_type:
self.src_dst_trainable_weights = self.encoder.get_weights() + self.inter.get_weights() + self.decoder_src.get_weights() + self.decoder_dst.get_weights() self.src_dst_saveable_weights = self.encoder.get_weights() + self.inter.get_weights() + self.decoder_src.get_weights() + self.decoder_dst.get_weights()
self.src_dst_trainable_weights = self.src_dst_saveable_weights
elif 'liae' in archi_type: elif 'liae' in archi_type:
self.src_dst_trainable_weights = self.encoder.get_weights() + self.inter_AB.get_weights() + self.inter_B.get_weights() + self.decoder.get_weights() self.src_dst_saveable_weights = self.encoder.get_weights() + self.inter_AB.get_weights() + self.inter_B.get_weights() + self.decoder.get_weights()
if random_warp:
self.src_dst_trainable_weights = self.src_dst_saveable_weights
else:
self.src_dst_trainable_weights = self.encoder.get_weights() + self.inter_B.get_weights() + self.decoder.get_weights()
self.src_dst_opt = OptimizerClass(lr=lr, lr_dropout=lr_dropout, clipnorm=clipnorm, name='src_dst_opt') self.src_dst_opt = OptimizerClass(lr=lr, lr_dropout=lr_dropout, lr_cos=lr_cos, clipnorm=clipnorm, name='src_dst_opt')
self.src_dst_opt.initialize_variables (self.src_dst_trainable_weights, vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu') self.src_dst_opt.initialize_variables (self.src_dst_saveable_weights, vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
self.model_filename_list += [ (self.src_dst_opt, 'src_dst_opt.npy') ] self.model_filename_list += [ (self.src_dst_opt, 'src_dst_opt.npy') ]
if self.options['true_face_power'] != 0: if self.options['true_face_power'] != 0:
self.D_code_opt = OptimizerClass(lr=lr, lr_dropout=lr_dropout, clipnorm=clipnorm, name='D_code_opt') self.D_code_opt = OptimizerClass(lr=lr, lr_dropout=lr_dropout, lr_cos=lr_cos, clipnorm=clipnorm, name='D_code_opt')
self.D_code_opt.initialize_variables ( self.code_discriminator.get_weights(), vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu') self.D_code_opt.initialize_variables ( self.code_discriminator.get_weights(), vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
self.model_filename_list += [ (self.D_code_opt, 'D_code_opt.npy') ] self.model_filename_list += [ (self.D_code_opt, 'D_code_opt.npy') ]
if gan_power != 0: if gan_power != 0:
self.D_src_dst_opt = OptimizerClass(lr=lr, lr_dropout=lr_dropout, clipnorm=clipnorm, name='GAN_opt') self.D_src_dst_opt = OptimizerClass(lr=lr, lr_dropout=lr_dropout, lr_cos=lr_cos, clipnorm=clipnorm, name='GAN_opt')
self.D_src_dst_opt.initialize_variables ( self.D_src.get_weights(), vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')#+self.D_src_x2.get_weights() self.D_src_dst_opt.initialize_variables ( self.D_src.get_weights(), vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')#+self.D_src_x2.get_weights()
self.model_filename_list += [ (self.D_src_dst_opt, 'GAN_opt.npy') ] self.model_filename_list += [ (self.D_src_dst_opt, 'GAN_opt.npy') ]
@ -375,18 +390,18 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
if blur_out_mask: if blur_out_mask:
sigma = resolution / 128 sigma = resolution / 128
x = nn.gaussian_blur(gpu_target_src*gpu_target_srcm_anti, sigma) x = nn.gaussian_blur(gpu_target_src*gpu_target_srcm_anti, sigma)
y = 1-nn.gaussian_blur(gpu_target_srcm, sigma) y = 1-nn.gaussian_blur(gpu_target_srcm, sigma)
y = tf.where(tf.equal(y, 0), tf.ones_like(y), y) y = tf.where(tf.equal(y, 0), tf.ones_like(y), y)
gpu_target_src = gpu_target_src*gpu_target_srcm + (x/y)*gpu_target_srcm_anti gpu_target_src = gpu_target_src*gpu_target_srcm + (x/y)*gpu_target_srcm_anti
x = nn.gaussian_blur(gpu_target_dst*gpu_target_dstm_anti, sigma) x = nn.gaussian_blur(gpu_target_dst*gpu_target_dstm_anti, sigma)
y = 1-nn.gaussian_blur(gpu_target_dstm, sigma) y = 1-nn.gaussian_blur(gpu_target_dstm, sigma)
y = tf.where(tf.equal(y, 0), tf.ones_like(y), y) y = tf.where(tf.equal(y, 0), tf.ones_like(y), y)
gpu_target_dst = gpu_target_dst*gpu_target_dstm + (x/y)*gpu_target_dstm_anti gpu_target_dst = gpu_target_dst*gpu_target_dstm + (x/y)*gpu_target_dstm_anti
# process model tensors # process model tensors
if 'df' in archi_type: if 'df' in archi_type:
gpu_src_code = self.inter(self.encoder(gpu_warped_src)) gpu_src_code = self.inter(self.encoder(gpu_warped_src))
@ -395,7 +410,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
gpu_pred_dst_dst, gpu_pred_dst_dstm = self.decoder_dst(gpu_dst_code) gpu_pred_dst_dst, gpu_pred_dst_dstm = self.decoder_dst(gpu_dst_code)
gpu_pred_src_dst, gpu_pred_src_dstm = self.decoder_src(gpu_dst_code) gpu_pred_src_dst, gpu_pred_src_dstm = self.decoder_src(gpu_dst_code)
gpu_pred_src_dst_no_code_grad, _ = self.decoder_src(tf.stop_gradient(gpu_dst_code)) gpu_pred_src_dst_no_code_grad, _ = self.decoder_src(tf.stop_gradient(gpu_dst_code))
elif 'liae' in archi_type: elif 'liae' in archi_type:
gpu_src_code = self.encoder (gpu_warped_src) gpu_src_code = self.encoder (gpu_warped_src)
gpu_src_inter_AB_code = self.inter_AB (gpu_src_code) gpu_src_inter_AB_code = self.inter_AB (gpu_src_code)
@ -425,11 +440,11 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
gpu_target_dstm_blur = nn.gaussian_blur(gpu_target_dstm, max(1, resolution // 32) ) gpu_target_dstm_blur = nn.gaussian_blur(gpu_target_dstm, max(1, resolution // 32) )
gpu_target_dstm_blur = tf.clip_by_value(gpu_target_dstm_blur, 0, 0.5) * 2 gpu_target_dstm_blur = tf.clip_by_value(gpu_target_dstm_blur, 0, 0.5) * 2
gpu_style_mask_blur = nn.gaussian_blur(gpu_pred_src_dstm*gpu_pred_dst_dstm, max(1, resolution // 32) ) gpu_style_mask_blur = nn.gaussian_blur(gpu_pred_src_dstm*gpu_pred_dst_dstm, max(1, resolution // 32) )
gpu_style_mask_blur = tf.stop_gradient(tf.clip_by_value(gpu_target_srcm_blur, 0, 1.0)) gpu_style_mask_blur = tf.stop_gradient(tf.clip_by_value(gpu_target_srcm_blur, 0, 1.0))
gpu_style_mask_anti_blur = 1.0 - gpu_style_mask_blur gpu_style_mask_anti_blur = 1.0 - gpu_style_mask_blur
gpu_target_dst_masked = gpu_target_dst*gpu_target_dstm_blur gpu_target_dst_masked = gpu_target_dst*gpu_target_dstm_blur
gpu_target_src_anti_masked = gpu_target_src*gpu_target_srcm_anti_blur gpu_target_src_anti_masked = gpu_target_src*gpu_target_srcm_anti_blur
@ -460,7 +475,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
if bg_style_power != 0 and not self.pretrain: if bg_style_power != 0 and not self.pretrain:
gpu_target_dst_style_anti_masked = gpu_target_dst*gpu_style_mask_anti_blur gpu_target_dst_style_anti_masked = gpu_target_dst*gpu_style_mask_anti_blur
gpu_psd_style_anti_masked = gpu_pred_src_dst*gpu_style_mask_anti_blur gpu_psd_style_anti_masked = gpu_pred_src_dst*gpu_style_mask_anti_blur
gpu_src_loss += tf.reduce_mean( (10*bg_style_power)*nn.dssim( gpu_psd_style_anti_masked, gpu_target_dst_style_anti_masked, max_val=1.0, filter_size=int(resolution/11.6)), axis=[1]) gpu_src_loss += tf.reduce_mean( (10*bg_style_power)*nn.dssim( gpu_psd_style_anti_masked, gpu_target_dst_style_anti_masked, max_val=1.0, filter_size=int(resolution/11.6)), axis=[1])
gpu_src_loss += tf.reduce_mean( (10*bg_style_power)*tf.square(gpu_psd_style_anti_masked - gpu_target_dst_style_anti_masked), axis=[1,2,3] ) gpu_src_loss += tf.reduce_mean( (10*bg_style_power)*tf.square(gpu_psd_style_anti_masked - gpu_target_dst_style_anti_masked), axis=[1,2,3] )
@ -659,8 +674,8 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
self.set_training_data_generators ([ self.set_training_data_generators ([
SampleGeneratorFace(training_data_src_path, random_ct_samples_path=random_ct_samples_path, debug=self.is_debug(), batch_size=self.get_batch_size(), SampleGeneratorFace(training_data_src_path, random_ct_samples_path=random_ct_samples_path, debug=self.is_debug(), batch_size=self.get_batch_size(),
sample_process_options=SampleProcessor.Options(scale_range=[-0.125, 0.125], random_flip=random_src_flip), sample_process_options=SampleProcessor.Options(scale_range=[-0.15, 0.15], random_flip=random_src_flip),
output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'random_hsv_shift_amount' : random_hsv_power, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': ct_mode, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.EYES_MOUTH, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.EYES_MOUTH, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
@ -669,7 +684,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
generators_count=src_generators_count ), generators_count=src_generators_count ),
SampleGeneratorFace(training_data_dst_path, debug=self.is_debug(), batch_size=self.get_batch_size(), SampleGeneratorFace(training_data_dst_path, debug=self.is_debug(), batch_size=self.get_batch_size(),
sample_process_options=SampleProcessor.Options(scale_range=[-0.125, 0.125], random_flip=random_dst_flip), sample_process_options=SampleProcessor.Options(scale_range=[-0.15, 0.15], random_flip=random_dst_flip),
output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},