mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-08-19 21:13:20 -07:00
Now options can be read from yaml file using --config-training-file arg in trainer
This commit is contained in:
Cioscos
commit
d0b5090879
8 changed files with 243 additions and 222 deletions
|
|
@ -104,7 +104,7 @@ def gen_pts(W, H, rnd_state=None):
|
|||
return pts1, pts2
|
||||
|
||||
|
||||
def gen_warp_params (w, flip=False, rotation_range=[-2,2], scale_range=[-0.5, 0.5], tx_range=[-0.05, 0.05], ty_range=[-0.05, 0.05], rnd_state=None ):
|
||||
def gen_warp_params (w, flip=False, rotation_range=[-2,2], scale_range=[-0.5, 0.5], tx_range=[-0.05, 0.05], ty_range=[-0.05, 0.05], rnd_state=None, warp_rnd_state=None):
|
||||
if rnd_state is None:
|
||||
rnd_state = np.random
|
||||
if warp_rnd_state is None:
|
||||
|
|
|
|||
|
|
@ -76,9 +76,11 @@ class PatchDiscriminator(nn.ModelBase):
|
|||
|
||||
nn.PatchDiscriminator = PatchDiscriminator
|
||||
|
||||
|
||||
class UNetPatchDiscriminator(nn.ModelBase):
|
||||
"""
|
||||
Inspired by https://arxiv.org/abs/2002.12655 "A U-Net Based Discriminator for Generative Adversarial Networks"
|
||||
Based on iperov commit 11add4cd4f5a61df26a8659f4cc5c8d9467bf5f8 from Jan 3, 2021 with added fp16 option
|
||||
"""
|
||||
def calc_receptive_field_size(self, layers):
|
||||
"""
|
||||
|
|
@ -133,6 +135,7 @@ class UNetPatchDiscriminator(nn.ModelBase):
|
|||
def on_build(self, patch_size, in_ch, base_ch = 16, use_fp16 = False):
|
||||
self.use_fp16 = use_fp16
|
||||
conv_dtype = tf.float16 if use_fp16 else tf.float32
|
||||
|
||||
class ResidualBlock(nn.ModelBase):
|
||||
def on_build(self, ch, kernel_size=3 ):
|
||||
self.conv1 = nn.Conv2D( ch, ch, kernel_size=kernel_size, padding='SAME', dtype=conv_dtype)
|
||||
|
|
@ -147,7 +150,11 @@ class UNetPatchDiscriminator(nn.ModelBase):
|
|||
|
||||
prev_ch = in_ch
|
||||
self.convs = []
|
||||
self.res1 = []
|
||||
self.res2 = []
|
||||
self.upconvs = []
|
||||
self.upres1 = []
|
||||
self.upres2 = []
|
||||
layers = self.find_archi(patch_size)
|
||||
|
||||
level_chs = { i-1:v for i,v in enumerate([ min( base_ch * (2**i), 512 ) for i in range(len(layers)+1)]) }
|
||||
|
|
@ -172,13 +179,10 @@ class UNetPatchDiscriminator(nn.ModelBase):
|
|||
|
||||
|
||||
def forward(self, x):
|
||||
if self.use_fp16:
|
||||
x = tf.cast(x, tf.float16)
|
||||
|
||||
x = tf.nn.leaky_relu( self.in_conv(x), 0.2 )
|
||||
|
||||
encs = []
|
||||
for conv in self.convs:
|
||||
for conv, res1,res2 in zip(self.convs, self.res1, self.res2):
|
||||
encs.insert(0, x)
|
||||
x = tf.nn.leaky_relu( conv(x), 0.2 )
|
||||
x = res1(x)
|
||||
|
|
@ -186,23 +190,20 @@ class UNetPatchDiscriminator(nn.ModelBase):
|
|||
|
||||
center_out, x = self.center_out(x), tf.nn.leaky_relu( self.center_conv(x), 0.2 )
|
||||
|
||||
for i, (upconv, enc) in enumerate(zip(self.upconvs, encs)):
|
||||
for i, (upconv, enc, upres1, upres2 ) in enumerate(zip(self.upconvs, encs, self.upres1, self.upres2)):
|
||||
x = tf.nn.leaky_relu( upconv(x), 0.2 )
|
||||
x = tf.concat( [enc, x], axis=nn.conv2d_ch_axis)
|
||||
x = upres1(x)
|
||||
x = upres2(x)
|
||||
|
||||
x = self.out_conv(x)
|
||||
|
||||
if self.use_fp16:
|
||||
center_out = tf.cast(center_out, tf.float32)
|
||||
x = tf.cast(x, tf.float32)
|
||||
|
||||
return center_out, x
|
||||
return center_out, self.out_conv(x)
|
||||
|
||||
nn.UNetPatchDiscriminator = UNetPatchDiscriminator
|
||||
|
||||
class UNetPatchDiscriminatorV2(nn.ModelBase):
|
||||
"""
|
||||
Inspired by https://arxiv.org/abs/2002.12655 "A U-Net Based Discriminator for Generative Adversarial Networks"
|
||||
Based on iperov commit 35877dbfd724c22040f421e93c1adbb7142e5b5d from Jul 14, 2021
|
||||
"""
|
||||
def calc_receptive_field_size(self, layers):
|
||||
"""
|
||||
|
|
@ -218,7 +219,7 @@ class UNetPatchDiscriminatorV2(nn.ModelBase):
|
|||
ts *= s
|
||||
return rf
|
||||
|
||||
def find_archi(self, target_patch_size, max_layers=6):
|
||||
def find_archi(self, target_patch_size, max_layers=9):
|
||||
"""
|
||||
Find the best configuration of layers using only 3x3 convs for target patch size
|
||||
"""
|
||||
|
|
@ -230,12 +231,12 @@ class UNetPatchDiscriminatorV2(nn.ModelBase):
|
|||
|
||||
layers = []
|
||||
sum_st = 0
|
||||
layers.append ( [3, 2])
|
||||
sum_st += 2
|
||||
for i in range(layers_count-1):
|
||||
st = 1 + (1 if val & (1 << i) !=0 else 0 )
|
||||
layers.append ( [3, st ])
|
||||
sum_st += st
|
||||
layers.append ( [3, 2])
|
||||
sum_st += 2
|
||||
|
||||
rf = self.calc_receptive_field_size(layers)
|
||||
|
||||
|
|
@ -244,7 +245,7 @@ class UNetPatchDiscriminatorV2(nn.ModelBase):
|
|||
s[rf] = (layers_count, sum_st, layers)
|
||||
else:
|
||||
if layers_count < s_rf[0] or \
|
||||
( layers_count == s_rf[0] and sum_st > s_rf[1] ):
|
||||
( layers_count == s_rf[0] and sum_st > s_rf[1] ):
|
||||
s[rf] = (layers_count, sum_st, layers)
|
||||
|
||||
if val == 0:
|
||||
|
|
@ -254,7 +255,7 @@ class UNetPatchDiscriminatorV2(nn.ModelBase):
|
|||
q=x[np.abs(np.array(x)-target_patch_size).argmin()]
|
||||
return s[q][2]
|
||||
|
||||
def on_build(self, patch_size, in_ch, use_fp16 = False):
|
||||
def on_build(self, patch_size, in_ch, base_ch = 16, use_fp16 = False):
|
||||
self.use_fp16 = use_fp16
|
||||
conv_dtype = tf.float16 if use_fp16 else tf.float32
|
||||
|
||||
|
|
@ -272,11 +273,8 @@ class UNetPatchDiscriminatorV2(nn.ModelBase):
|
|||
|
||||
prev_ch = in_ch
|
||||
self.convs = []
|
||||
self.res = []
|
||||
self.upconvs = []
|
||||
self.upres = []
|
||||
layers = self.find_archi(patch_size)
|
||||
base_ch = 16
|
||||
|
||||
level_chs = { i-1:v for i,v in enumerate([ min( base_ch * (2**i), 512 ) for i in range(len(layers)+1)]) }
|
||||
|
||||
|
|
@ -285,12 +283,8 @@ class UNetPatchDiscriminatorV2(nn.ModelBase):
|
|||
for i, (kernel_size, strides) in enumerate(layers):
|
||||
self.convs.append ( nn.Conv2D( level_chs[i-1], level_chs[i], kernel_size=kernel_size, strides=strides, padding='SAME', dtype=conv_dtype) )
|
||||
|
||||
self.res.append ( ResidualBlock(level_chs[i]) )
|
||||
|
||||
self.upconvs.insert (0, nn.Conv2DTranspose( level_chs[i]*(2 if i != len(layers)-1 else 1), level_chs[i-1], kernel_size=kernel_size, strides=strides, padding='SAME', dtype=conv_dtype) )
|
||||
|
||||
self.upres.insert (0, ResidualBlock(level_chs[i-1]*2) )
|
||||
|
||||
self.out_conv = nn.Conv2D( level_chs[-1]*2, 1, kernel_size=1, padding='VALID', dtype=conv_dtype)
|
||||
|
||||
self.center_out = nn.Conv2D( level_chs[len(layers)-1], 1, kernel_size=1, padding='VALID', dtype=conv_dtype)
|
||||
|
|
@ -301,20 +295,18 @@ class UNetPatchDiscriminatorV2(nn.ModelBase):
|
|||
if self.use_fp16:
|
||||
x = tf.cast(x, tf.float16)
|
||||
|
||||
x = tf.nn.leaky_relu( self.in_conv(x), 0.1 )
|
||||
x = tf.nn.leaky_relu( self.in_conv(x), 0.2 )
|
||||
|
||||
encs = []
|
||||
for conv, res in zip(self.convs, self.res):
|
||||
for conv in self.convs:
|
||||
encs.insert(0, x)
|
||||
x = tf.nn.leaky_relu( conv(x), 0.1 )
|
||||
x = res(x)
|
||||
x = tf.nn.leaky_relu( conv(x), 0.2 )
|
||||
|
||||
center_out, x = self.center_out(x), self.center_conv(x)
|
||||
center_out, x = self.center_out(x), tf.nn.leaky_relu( self.center_conv(x), 0.2 )
|
||||
|
||||
for i, (upconv, enc, upres) in enumerate(zip(self.upconvs, encs, self.upres)):
|
||||
x = tf.nn.leaky_relu( upconv(x), 0.1 )
|
||||
for i, (upconv, enc) in enumerate(zip(self.upconvs, encs)):
|
||||
x = tf.nn.leaky_relu( upconv(x), 0.2 )
|
||||
x = tf.concat( [enc, x], axis=nn.conv2d_ch_axis)
|
||||
x = upres(x)
|
||||
|
||||
x = self.out_conv(x)
|
||||
|
||||
|
|
|
|||
|
|
@ -25,13 +25,17 @@ class TensorBoardTool:
|
|||
def run(self):
|
||||
from tensorboard import default
|
||||
from tensorboard import program
|
||||
from tensorboard import version as tb_version
|
||||
# remove http messages
|
||||
log = logging.getLogger('werkzeug').setLevel(logging.ERROR)
|
||||
# Start tensorboard server
|
||||
tb = program.TensorBoard(default.get_plugins())
|
||||
tb.configure(argv=[None, '--logdir', self.dir_path, '--port', '6006', '--bind_all'])
|
||||
tb_argv = [None, '--logdir', self.dir_path, '--port', '6006']
|
||||
if int(tb_version.VERSION[0])>=2:
|
||||
tb_argv.append("--bind_all")
|
||||
tb.configure(argv=tb_argv)
|
||||
url = tb.launch()
|
||||
print('Launched TensorBoard at {}'.format(url))
|
||||
io.log_info('Launched TensorBoard at {}\n'.format(url))
|
||||
|
||||
def process_img_for_tensorboard(input_img):
|
||||
# convert format from bgr to rgb
|
||||
|
|
@ -127,6 +131,25 @@ def trainerThread (s2c, c2s, e,
|
|||
if not debug and not is_reached_goal:
|
||||
model.create_backup()
|
||||
|
||||
def log_step(step, step_time, src_loss, dst_loss):
|
||||
c2s.put({
|
||||
'op': 'tb',
|
||||
'action': 'step',
|
||||
'step': step,
|
||||
'step_time': step_time,
|
||||
'src_loss': src_loss,
|
||||
'dst_loss': dst_loss
|
||||
})
|
||||
|
||||
def log_previews(step, previews, static_previews):
|
||||
c2s.put({
|
||||
'op': 'tb',
|
||||
'action': 'preview',
|
||||
'step': step,
|
||||
'previews': previews,
|
||||
'static_previews': static_previews
|
||||
})
|
||||
|
||||
def send_preview():
|
||||
if not debug:
|
||||
previews = model.get_previews()
|
||||
|
|
@ -324,7 +347,6 @@ def handle_tensorboard_op(input):
|
|||
log_tensorboard_previews(step, previews, 'preview', train_summary_writer)
|
||||
if static_previews is not None:
|
||||
log_tensorboard_previews(step, static_previews, 'static_preview', train_summary_writer)
|
||||
c2s.put({'op': 'close'})
|
||||
|
||||
|
||||
class Zoom(Enum):
|
||||
|
|
@ -586,7 +608,7 @@ def main(**kwargs):
|
|||
selected_preview = selected_preview % len(previews)
|
||||
update_preview = True
|
||||
elif op == 'tb':
|
||||
handle_tensorboard_op(input)
|
||||
handle_tensorboard_op(item)
|
||||
elif op == 'close':
|
||||
break
|
||||
|
||||
|
|
|
|||
|
|
@ -142,9 +142,10 @@ class ModelBase(object):
|
|||
self.sample_for_preview = None
|
||||
self.choosed_gpu_indexes = None
|
||||
|
||||
# MODIFY HERE!!! ---------------------------------------------------------------------------------------
|
||||
model_data = {}
|
||||
# True if yaml conf file exists
|
||||
self.config_file_exists = False
|
||||
# True if user chooses to read options from conf file
|
||||
self.read_from_conf = False
|
||||
#check if config_training_file mode is enabled
|
||||
if config_training_file is not None:
|
||||
|
|
@ -169,6 +170,7 @@ class ModelBase(object):
|
|||
model_data = pickle.loads ( self.model_data_path.read_bytes() )
|
||||
self.iter = model_data.get('iter',0)
|
||||
if self.iter != 0:
|
||||
# read options from the .dat file only if the user chooses not to read options from the yaml file
|
||||
if not self.config_file_exists:
|
||||
self.options = model_data['options']
|
||||
self.loss_history = model_data.get('loss_history', [])
|
||||
|
|
@ -420,6 +422,9 @@ class ModelBase(object):
|
|||
def get_previews(self):
|
||||
return self.onGetPreview ( self.last_sample )
|
||||
|
||||
def get_static_previews(self):
|
||||
return self.onGetPreview (self.sample_for_preview)
|
||||
|
||||
def get_history_previews(self):
|
||||
return self.onGetPreview (self.sample_for_preview, for_history=True)
|
||||
|
||||
|
|
@ -453,10 +458,17 @@ class ModelBase(object):
|
|||
self.create_backup()
|
||||
|
||||
def read_from_config_file(self):
|
||||
"""
|
||||
Read yaml config file and saves it into a dictionary
|
||||
Returns:
|
||||
[type]: [description]
|
||||
"""
|
||||
with open(self.config_file_path, 'r') as file:
|
||||
data = yaml.safe_load(file)
|
||||
|
||||
for key, value in data.items():
|
||||
if isinstance(value, bool):
|
||||
continue
|
||||
if isinstance(value, int):
|
||||
data[key] = np.int32(value)
|
||||
elif isinstance(value, float):
|
||||
|
|
@ -465,6 +477,9 @@ class ModelBase(object):
|
|||
return data
|
||||
|
||||
def save_config_file(self):
|
||||
"""
|
||||
Saves options dictionary in a yaml file
|
||||
"""
|
||||
saving_dict = {}
|
||||
for key, value in self.options.items():
|
||||
if isinstance(value, np.int32) or isinstance(value, np.float64):
|
||||
|
|
@ -473,7 +488,7 @@ class ModelBase(object):
|
|||
saving_dict[key] = value
|
||||
|
||||
with open(self.config_file_path, 'w') as file:
|
||||
yaml.dump(saving_dict, file)
|
||||
yaml.dump(saving_dict, file, sort_keys=False)
|
||||
|
||||
def create_backup(self):
|
||||
io.log_info ("Creating backup...", end='\r')
|
||||
|
|
@ -607,8 +622,6 @@ class ModelBase(object):
|
|||
def get_strpath_storage_for_file(self, filename):
|
||||
return str( self.saved_models_path / ( self.get_model_name() + '_' + filename) )
|
||||
|
||||
|
||||
|
||||
def get_summary_path(self):
|
||||
return self.get_strpath_storage_for_file('summary.txt')
|
||||
|
||||
|
|
|
|||
|
|
@ -51,24 +51,27 @@ class AMPModel(ModelBase):
|
|||
default_ct_mode = self.options['ct_mode'] = self.load_or_def_option('ct_mode', 'none')
|
||||
default_random_color = self.options['random_color'] = self.load_or_def_option('random_color', False)
|
||||
default_clipgrad = self.options['clipgrad'] = self.load_or_def_option('clipgrad', False)
|
||||
default_use_fp16 = self.options['use_fp16'] = self.load_or_def_option('use_fp16', False)
|
||||
|
||||
ask_override = self.ask_override()
|
||||
ask_override = False if self.read_from_conf else self.ask_override()
|
||||
if self.is_first_run() or ask_override:
|
||||
self.ask_autobackup_hour()
|
||||
self.ask_write_preview_history()
|
||||
self.ask_target_iter()
|
||||
self.ask_retraining_samples()
|
||||
self.ask_random_src_flip()
|
||||
self.ask_random_dst_flip()
|
||||
self.ask_batch_size(8)
|
||||
# self.options['use_fp16'] = io.input_bool ("Use fp16", default_usefp16, help_message='Increases training/inference speed, reduces model size. Model may crash. Enable it after 1-5k iters.')
|
||||
if (self.read_from_conf and not self.config_file_exists) or not self.read_from_conf:
|
||||
self.ask_autobackup_hour()
|
||||
self.ask_write_preview_history()
|
||||
self.ask_target_iter()
|
||||
self.ask_retraining_samples()
|
||||
self.ask_random_src_flip()
|
||||
self.ask_random_dst_flip()
|
||||
self.ask_batch_size(8)
|
||||
# self.options['use_fp16'] = io.input_bool ("Use fp16", default_usefp16, help_message='Increases training/inference speed, reduces model size. Model may crash. Enable it after 1-5k iters.')
|
||||
|
||||
|
||||
if self.is_first_run():
|
||||
resolution = io.input_int("Resolution", default_resolution, add_info="64-640", help_message="More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 32 .")
|
||||
resolution = np.clip ( (resolution // 32) * 32, 64, 640)
|
||||
self.options['resolution'] = resolution
|
||||
self.options['face_type'] = io.input_str ("Face type", default_face_type, ['f','wf','head'], help_message="whole face / head").lower()
|
||||
if (self.read_from_conf and not self.config_file_exists) or not self.read_from_conf:
|
||||
resolution = io.input_int("Resolution", default_resolution, add_info="64-640", help_message="More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 32 .")
|
||||
resolution = np.clip ( (resolution // 32) * 32, 64, 640)
|
||||
self.options['resolution'] = resolution
|
||||
self.options['face_type'] = io.input_str ("Face type", default_face_type, ['f','wf','head'], help_message="whole face / head").lower()
|
||||
|
||||
|
||||
default_d_dims = self.options['d_dims'] = self.load_or_def_option('d_dims', 64)
|
||||
|
|
@ -78,59 +81,62 @@ class AMPModel(ModelBase):
|
|||
default_d_mask_dims = self.options['d_mask_dims'] = self.load_or_def_option('d_mask_dims', default_d_mask_dims)
|
||||
|
||||
if self.is_first_run():
|
||||
self.options['ae_dims'] = np.clip ( io.input_int("AutoEncoder dimensions", default_ae_dims, add_info="32-1024", help_message="All face information will packed to AE dims. If amount of AE dims are not enough, then for example closed eyes will not be recognized. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU." ), 32, 1024 )
|
||||
self.options['inter_dims'] = np.clip ( io.input_int("Inter dimensions", default_inter_dims, add_info="32-2048", help_message="Should be equal or more than AutoEncoder dimensions. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU." ), 32, 2048 )
|
||||
if (self.read_from_conf and not self.config_file_exists) or not self.read_from_conf:
|
||||
self.options['ae_dims'] = np.clip ( io.input_int("AutoEncoder dimensions", default_ae_dims, add_info="32-1024", help_message="All face information will packed to AE dims. If amount of AE dims are not enough, then for example closed eyes will not be recognized. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU." ), 32, 1024 )
|
||||
self.options['inter_dims'] = np.clip ( io.input_int("Inter dimensions", default_inter_dims, add_info="32-2048", help_message="Should be equal or more than AutoEncoder dimensions. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU." ), 32, 2048 )
|
||||
|
||||
e_dims = np.clip ( io.input_int("Encoder dimensions", default_e_dims, add_info="16-256", help_message="More dims help to recognize more facial features and achieve sharper result, but require more VRAM. You can fine-tune model size to fit your GPU." ), 16, 256 )
|
||||
self.options['e_dims'] = e_dims + e_dims % 2
|
||||
e_dims = np.clip ( io.input_int("Encoder dimensions", default_e_dims, add_info="16-256", help_message="More dims help to recognize more facial features and achieve sharper result, but require more VRAM. You can fine-tune model size to fit your GPU." ), 16, 256 )
|
||||
self.options['e_dims'] = e_dims + e_dims % 2
|
||||
|
||||
d_dims = np.clip ( io.input_int("Decoder dimensions", default_d_dims, add_info="16-256", help_message="More dims help to recognize more facial features and achieve sharper result, but require more VRAM. You can fine-tune model size to fit your GPU." ), 16, 256 )
|
||||
self.options['d_dims'] = d_dims + d_dims % 2
|
||||
d_dims = np.clip ( io.input_int("Decoder dimensions", default_d_dims, add_info="16-256", help_message="More dims help to recognize more facial features and achieve sharper result, but require more VRAM. You can fine-tune model size to fit your GPU." ), 16, 256 )
|
||||
self.options['d_dims'] = d_dims + d_dims % 2
|
||||
|
||||
d_mask_dims = np.clip ( io.input_int("Decoder mask dimensions", default_d_mask_dims, add_info="16-256", help_message="Typical mask dimensions = decoder dimensions / 3. If you manually cut out obstacles from the dst mask, you can increase this parameter to achieve better quality." ), 16, 256 )
|
||||
self.options['d_mask_dims'] = d_mask_dims + d_mask_dims % 2
|
||||
d_mask_dims = np.clip ( io.input_int("Decoder mask dimensions", default_d_mask_dims, add_info="16-256", help_message="Typical mask dimensions = decoder dimensions / 3. If you manually cut out obstacles from the dst mask, you can increase this parameter to achieve better quality." ), 16, 256 )
|
||||
self.options['d_mask_dims'] = d_mask_dims + d_mask_dims % 2
|
||||
|
||||
morph_factor = np.clip ( io.input_number ("Morph factor.", default_morph_factor, add_info="0.1 .. 0.5", help_message="Typical fine value is 0.5"), 0.1, 0.5 )
|
||||
self.options['morph_factor'] = morph_factor
|
||||
morph_factor = np.clip ( io.input_number ("Morph factor.", default_morph_factor, add_info="0.1 .. 0.5", help_message="Typical fine value is 0.5"), 0.1, 0.5 )
|
||||
self.options['morph_factor'] = morph_factor
|
||||
|
||||
if self.is_first_run() or ask_override:
|
||||
self.options['eyes_mouth_prio'] = io.input_bool ("Eyes and mouth priority", default_eyes_mouth_prio, help_message='Helps to fix eye problems during training like "alien eyes" and wrong eyes direction. Also makes the detail of the teeth higher.')
|
||||
self.options['uniform_yaw'] = io.input_bool ("Uniform yaw distribution of samples", default_uniform_yaw, help_message='Helps to fix blurry side faces due to small amount of them in the faceset.')
|
||||
if (self.read_from_conf and not self.config_file_exists) or not self.read_from_conf:
|
||||
self.options['eyes_mouth_prio'] = io.input_bool ("Eyes and mouth priority", default_eyes_mouth_prio, help_message='Helps to fix eye problems during training like "alien eyes" and wrong eyes direction. Also makes the detail of the teeth higher.')
|
||||
self.options['uniform_yaw'] = io.input_bool ("Uniform yaw distribution of samples", default_uniform_yaw, help_message='Helps to fix blurry side faces due to small amount of them in the faceset.')
|
||||
|
||||
self.options['blur_out_mask'] = io.input_bool ("Blur out mask", default_blur_out_mask, help_message='Blurs nearby area outside of applied face mask of training samples. The result is the background near the face is smoothed and less noticeable on swapped face. The exact xseg mask in src and dst faceset is required.')
|
||||
self.options['blur_out_mask'] = io.input_bool ("Blur out mask", default_blur_out_mask, help_message='Blurs nearby area outside of applied face mask of training samples. The result is the background near the face is smoothed and less noticeable on swapped face. The exact xseg mask in src and dst faceset is required.')
|
||||
|
||||
self.options['lr_dropout'] = io.input_str (f"Use learning rate dropout", default_lr_dropout, ['n','y','cpu'], help_message="When the face is trained enough, you can enable this option to get extra sharpness and reduce subpixel shake for less amount of iterations. Enabled it before `disable random warp` and before GAN. \nn - disabled.\ny - enabled\ncpu - enabled on CPU. This allows not to use extra VRAM, sacrificing 20% time of iteration.")
|
||||
self.options['lr_dropout'] = io.input_str (f"Use learning rate dropout", default_lr_dropout, ['n','y','cpu'], help_message="When the face is trained enough, you can enable this option to get extra sharpness and reduce subpixel shake for less amount of iterations. Enabled it before `disable random warp` and before GAN. \nn - disabled.\ny - enabled\ncpu - enabled on CPU. This allows not to use extra VRAM, sacrificing 20% time of iteration.")
|
||||
|
||||
default_gan_power = self.options['gan_power'] = self.load_or_def_option('gan_power', 0.0)
|
||||
default_gan_patch_size = self.options['gan_patch_size'] = self.load_or_def_option('gan_patch_size', self.options['resolution'] // 8)
|
||||
default_gan_dims = self.options['gan_dims'] = self.load_or_def_option('gan_dims', 16)
|
||||
|
||||
if self.is_first_run() or ask_override:
|
||||
self.options['models_opt_on_gpu'] = io.input_bool ("Place models and optimizer on GPU", default_models_opt_on_gpu, help_message="When you train on one GPU, by default model and optimizer weights are placed on GPU to accelerate the process. You can place they on CPU to free up extra VRAM, thus set bigger dimensions.")
|
||||
if (self.read_from_conf and not self.config_file_exists) or not self.read_from_conf:
|
||||
self.options['models_opt_on_gpu'] = io.input_bool ("Place models and optimizer on GPU", default_models_opt_on_gpu, help_message="When you train on one GPU, by default model and optimizer weights are placed on GPU to accelerate the process. You can place they on CPU to free up extra VRAM, thus set bigger dimensions.")
|
||||
|
||||
self.options['adabelief'] = io.input_bool ("Use AdaBelief optimizer?", default_adabelief, help_message="Use AdaBelief optimizer. It requires more VRAM, but the accuracy and the generalization of the model is higher.")
|
||||
self.options['adabelief'] = io.input_bool ("Use AdaBelief optimizer?", default_adabelief, help_message="Use AdaBelief optimizer. It requires more VRAM, but the accuracy and the generalization of the model is higher.")
|
||||
|
||||
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_downsample'] = io.input_bool("Enable random downsample of samples", default_random_downsample, help_message="")
|
||||
self.options['random_noise'] = io.input_bool("Enable random noise added to samples", default_random_noise, help_message="")
|
||||
self.options['random_blur'] = io.input_bool("Enable random blur of samples", default_random_blur, help_message="")
|
||||
self.options['random_jpeg'] = io.input_bool("Enable random jpeg compression of samples", default_random_jpeg, help_message="")
|
||||
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_downsample'] = io.input_bool("Enable random downsample of samples", default_random_downsample, help_message="")
|
||||
self.options['random_noise'] = io.input_bool("Enable random noise added to samples", default_random_noise, help_message="")
|
||||
self.options['random_blur'] = io.input_bool("Enable random blur of samples", default_random_blur, help_message="")
|
||||
self.options['random_jpeg'] = io.input_bool("Enable random jpeg compression of samples", default_random_jpeg, help_message="")
|
||||
|
||||
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 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 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:
|
||||
gan_patch_size = np.clip ( io.input_int("GAN patch size", default_gan_patch_size, add_info="3-640", help_message="The higher patch size, the higher the quality, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is resolution / 8." ), 3, 640 )
|
||||
self.options['gan_patch_size'] = gan_patch_size
|
||||
if self.options['gan_power'] != 0.0:
|
||||
gan_patch_size = np.clip ( io.input_int("GAN patch size", default_gan_patch_size, add_info="3-640", help_message="The higher patch size, the higher the quality, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is resolution / 8." ), 3, 640 )
|
||||
self.options['gan_patch_size'] = gan_patch_size
|
||||
|
||||
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-512", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 512 )
|
||||
self.options['gan_dims'] = gan_dims
|
||||
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-512", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 512 )
|
||||
self.options['gan_dims'] = gan_dims
|
||||
|
||||
#self.options['background_power'] = np.clip ( io.input_number("Background power", default_background_power, add_info="0.0..1.0", help_message="Learn the area outside of the mask. Helps smooth out area near the mask boundaries. Can be used at any time"), 0.0, 1.0 )
|
||||
#self.options['background_power'] = np.clip ( io.input_number("Background power", default_background_power, add_info="0.0..1.0", help_message="Learn the area outside of the mask. Helps smooth out area near the mask boundaries. Can be used at any time"), 0.0, 1.0 )
|
||||
|
||||
self.options['ct_mode'] = io.input_str (f"Color transfer for src faceset", default_ct_mode, ['none','rct','lct','mkl','idt','sot', 'fs-aug'], help_message="Change color distribution of src samples close to dst samples. Try all modes to find the best.")
|
||||
self.options['random_color'] = io.input_bool ("Random color", default_random_color, help_message="Samples are randomly rotated around the L axis in LAB colorspace, helps generalize training")
|
||||
self.options['ct_mode'] = io.input_str (f"Color transfer for src faceset", default_ct_mode, ['none','rct','lct','mkl','idt','sot', 'fs-aug'], help_message="Change color distribution of src samples close to dst samples. Try all modes to find the best.")
|
||||
self.options['random_color'] = io.input_bool ("Random color", default_random_color, help_message="Samples are randomly rotated around the L axis in LAB colorspace, helps generalize training")
|
||||
|
||||
self.options['clipgrad'] = io.input_bool ("Enable gradient clipping", default_clipgrad, help_message="Gradient clipping reduces chance of model collapse, sacrificing speed of training.")
|
||||
self.options['clipgrad'] = io.input_bool ("Enable gradient clipping", default_clipgrad, help_message="Gradient clipping reduces chance of model collapse, sacrificing speed of training.")
|
||||
|
||||
self.gan_model_changed = (default_gan_patch_size != self.options['gan_patch_size']) or (default_gan_dims != self.options['gan_dims'])
|
||||
|
||||
|
|
@ -167,7 +173,7 @@ class AMPModel(ModelBase):
|
|||
|
||||
adabelief = self.options['adabelief']
|
||||
|
||||
# use_fp16 = self.options['use_fp16']
|
||||
use_fp16 = self.options['use_fp16']
|
||||
if self.is_exporting:
|
||||
use_fp16 = io.input_bool ("Export quantized?", False, help_message='Makes the exported model faster. If you have problems, disable this option.')
|
||||
|
||||
|
|
|
|||
|
|
@ -68,8 +68,9 @@ class SAEHDModel(ModelBase):
|
|||
default_random_color = self.options['random_color'] = self.load_or_def_option('random_color', False)
|
||||
default_clipgrad = self.options['clipgrad'] = self.load_or_def_option('clipgrad', False)
|
||||
default_pretrain = self.options['pretrain'] = self.load_or_def_option('pretrain', False)
|
||||
default_use_fp16 = self.options['use_fp16'] = self.load_or_def_option('use_fp16', False)
|
||||
|
||||
ask_override = self.ask_override()
|
||||
ask_override = False if self.read_from_conf else self.ask_override()
|
||||
if self.is_first_run() or ask_override:
|
||||
if (self.read_from_conf and not self.config_file_exists) or not self.read_from_conf:
|
||||
self.ask_session_name()
|
||||
|
|
@ -155,6 +156,7 @@ class SAEHDModel(ModelBase):
|
|||
self.options['blur_out_mask'] = io.input_bool ("Blur out mask", default_blur_out_mask, help_message='Blurs nearby area outside of applied face mask of training samples. The result is the background near the face is smoothed and less noticeable on swapped face. The exact xseg mask in src and dst faceset is required.')
|
||||
|
||||
default_gan_power = self.options['gan_power'] = self.load_or_def_option('gan_power', 0.0)
|
||||
default_gan_version = self.options['gan_version'] = self.load_or_def_option('gan_version', 2)
|
||||
default_gan_patch_size = self.options['gan_patch_size'] = self.load_or_def_option('gan_patch_size', self.options['resolution'] // 8)
|
||||
default_gan_dims = self.options['gan_dims'] = self.load_or_def_option('gan_dims', 16)
|
||||
default_gan_smoothing = self.options['gan_smoothing'] = self.load_or_def_option('gan_smoothing', 0.1)
|
||||
|
|
@ -182,13 +184,15 @@ class SAEHDModel(ModelBase):
|
|||
|
||||
self.options['gan_power'] = np.clip ( io.input_number ("GAN power", default_gan_power, add_info="0.0 .. 10.0", help_message="Train the network in Generative Adversarial manner. Forces the neural network to learn small details of the face. Enable it only when the face is trained enough and don't disable. Typical value is 0.1"), 0.0, 10.0 )
|
||||
|
||||
if self.options['gan_power'] != 0.0:
|
||||
if self.options['gan_version'] == 3:
|
||||
gan_patch_size = np.clip ( io.input_int("GAN patch size", default_gan_patch_size, add_info="3-640", help_message="The higher patch size, the higher the quality, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is resolution / 8." ), 3, 640 )
|
||||
self.options['gan_patch_size'] = gan_patch_size
|
||||
if self.options['gan_power'] != 0.0:
|
||||
self.options['gan_version'] = np.clip (io.input_int("GAN version", default_gan_version, add_info="2 or 3", help_message="Choose GAN version (v2: 7/16/2020, v3: 1/3/2021):"), 2, 3)
|
||||
|
||||
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-64", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 64 )
|
||||
self.options['gan_dims'] = gan_dims
|
||||
if self.options['gan_version'] == 3:
|
||||
gan_patch_size = np.clip ( io.input_int("GAN patch size", default_gan_patch_size, add_info="3-640", help_message="The higher patch size, the higher the quality, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is resolution / 8." ), 3, 640 )
|
||||
self.options['gan_patch_size'] = gan_patch_size
|
||||
|
||||
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-64", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 64 )
|
||||
self.options['gan_dims'] = gan_dims
|
||||
|
||||
self.options['gan_smoothing'] = np.clip ( io.input_number("GAN label smoothing", default_gan_smoothing, add_info="0 - 0.5", help_message="Uses soft labels with values slightly off from 0/1 for GAN, has a regularizing effect"), 0, 0.5)
|
||||
self.options['gan_noise'] = np.clip ( io.input_number("GAN noisy labels", default_gan_noise, add_info="0 - 0.5", help_message="Marks some images with the wrong label, helps prevent collapse"), 0, 0.5)
|
||||
|
|
@ -258,10 +262,6 @@ class SAEHDModel(ModelBase):
|
|||
if self.is_exporting:
|
||||
use_fp16 = io.input_bool ("Export quantized?", False, help_message='Makes the exported model faster. If you have problems, disable this option.')
|
||||
|
||||
use_fp16 = False
|
||||
if self.is_exporting:
|
||||
use_fp16 = io.input_bool ("Export quantized?", False, help_message='Makes the exported model faster. If you have problems, disable this option.')
|
||||
|
||||
self.gan_power = gan_power = 0.0 if self.pretrain else self.options['gan_power']
|
||||
random_warp = False if self.pretrain else self.options['random_warp']
|
||||
random_src_flip = self.random_src_flip if not self.pretrain else True
|
||||
|
|
@ -445,22 +445,6 @@ class SAEHDModel(ModelBase):
|
|||
y = tf.where(tf.equal(y, 0), tf.ones_like(y), y)
|
||||
gpu_target_dst = gpu_target_dst*gpu_target_dstm_all + (x/y)*gpu_target_dstm_anti
|
||||
|
||||
gpu_target_srcm_anti = 1-gpu_target_srcm
|
||||
gpu_target_dstm_anti = 1-gpu_target_dstm
|
||||
|
||||
if blur_out_mask:
|
||||
sigma = resolution / 128
|
||||
|
||||
x = nn.gaussian_blur(gpu_target_src*gpu_target_srcm_anti, sigma)
|
||||
y = 1-nn.gaussian_blur(gpu_target_srcm, sigma)
|
||||
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
|
||||
|
||||
x = nn.gaussian_blur(gpu_target_dst*gpu_target_dstm_anti, sigma)
|
||||
y = 1-nn.gaussian_blur(gpu_target_dstm, sigma)
|
||||
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
|
||||
|
||||
|
||||
# process model tensors
|
||||
if 'df' in archi_type:
|
||||
|
|
@ -827,7 +811,7 @@ class SAEHDModel(ModelBase):
|
|||
'random_noise': self.options['random_noise'],
|
||||
'random_blur': self.options['random_blur'],
|
||||
'random_jpeg': self.options['random_jpeg'],
|
||||
'transform':True, 'channel_type' : channel_type, 'ct_mode': ct_mode,
|
||||
'transform':True, 'channel_type' : channel_type, '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' : channel_type, '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},
|
||||
|
|
|
|||
|
|
@ -9,3 +9,5 @@ scipy==1.4.1
|
|||
colorama
|
||||
tensorflow-gpu==2.4.0
|
||||
tf2onnx==1.9.3
|
||||
tensorboardX
|
||||
crc32c
|
||||
|
|
|
|||
|
|
@ -12,3 +12,5 @@ pyqt5
|
|||
tf2onnx==1.9.3
|
||||
Flask==1.1.1
|
||||
flask-socketio==4.2.1
|
||||
tensorboardX
|
||||
crc32c
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue