mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-07-16 10:03:41 -07:00
SAEHD:
'models_opt_on_gpu' option is now available for multigpus (before only for 1 gpu) max resolution is now 512
This commit is contained in:
Colombo
parent
810dc5ada5
commit
74999ce7ee
1 changed files with 59 additions and 22 deletions
|
|
@ -58,8 +58,8 @@ class SAEHDModel(ModelBase):
|
|||
self.ask_batch_size(suggest_batch_size)
|
||||
|
||||
if self.is_first_run():
|
||||
resolution = io.input_int("Resolution", default_resolution, add_info="64-256", help_message="More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16.")
|
||||
resolution = np.clip ( (resolution // 16) * 16, 64, 256)
|
||||
resolution = io.input_int("Resolution", default_resolution, add_info="64-512", help_message="More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16.")
|
||||
resolution = np.clip ( (resolution // 16) * 16, 64, 512)
|
||||
self.options['resolution'] = resolution
|
||||
self.options['face_type'] = io.input_str ("Face type", default_face_type, ['h','mf','f','wf'], help_message="Half / mid face / full face / whole face. Half face has better resolution, but covers less area of cheeks. Mid face is 30% wider than half face. 'Whole face' covers full area of face include forehead, but requires manual merge in Adobe After Effects.").lower()
|
||||
self.options['archi'] = io.input_str ("AE architecture", default_archi, ['dfhd','liaehd','df','liae'], help_message="'df' keeps faces more natural. 'liae' can fix overly different face shapes. 'hd' is heavyweight version for the best quality.").lower()
|
||||
|
|
@ -67,7 +67,6 @@ class SAEHDModel(ModelBase):
|
|||
default_d_dims = 48 if self.options['archi'] == 'dfhd' else 64
|
||||
default_d_dims = self.options['d_dims'] = self.load_or_def_option('d_dims', default_d_dims)
|
||||
|
||||
|
||||
default_d_mask_dims = default_d_dims // 3
|
||||
default_d_mask_dims += default_d_mask_dims % 2
|
||||
default_d_mask_dims = self.options['d_mask_dims'] = self.load_or_def_option('d_mask_dims', default_d_mask_dims)
|
||||
|
|
@ -93,8 +92,7 @@ class SAEHDModel(ModelBase):
|
|||
self.options['eyes_prio'] = io.input_bool ("Eyes priority", default_eyes_prio, help_message='Helps to fix eye problems during training like "alien eyes" and wrong eyes direction ( especially on HD architectures ) by forcing the neural network to train eyes with higher priority. before/after https://i.imgur.com/YQHOuSR.jpg ')
|
||||
|
||||
if self.is_first_run() or ask_override:
|
||||
if len(device_config.devices) == 1:
|
||||
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['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['lr_dropout'] = io.input_bool ("Use learning rate 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.")
|
||||
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 for less amount of iterations.")
|
||||
|
|
@ -361,7 +359,7 @@ class SAEHDModel(ModelBase):
|
|||
|
||||
masked_training = self.options['masked_training']
|
||||
|
||||
models_opt_on_gpu = False if len(devices) == 0 else True if len(devices) > 1 else self.options['models_opt_on_gpu']
|
||||
models_opt_on_gpu = False if len(devices) == 0 else self.options['models_opt_on_gpu']
|
||||
models_opt_device = '/GPU:0' if models_opt_on_gpu and self.is_training else '/CPU:0'
|
||||
optimizer_vars_on_cpu = models_opt_device=='/CPU:0'
|
||||
|
||||
|
|
@ -426,8 +424,8 @@ class SAEHDModel(ModelBase):
|
|||
|
||||
if self.is_training:
|
||||
if gan_power != 0:
|
||||
self.D_src = nn.PatchDiscriminator(patch_size=resolution//16, in_ch=output_ch, base_ch=512, name="D_src")
|
||||
self.D_dst = nn.PatchDiscriminator(patch_size=resolution//16, in_ch=output_ch, base_ch=512, name="D_dst")
|
||||
self.D_src = nn.PatchDiscriminator(patch_size=resolution//16, in_ch=output_ch, name="D_src")
|
||||
self.D_dst = nn.PatchDiscriminator(patch_size=resolution//16, in_ch=output_ch, name="D_dst")
|
||||
self.model_filename_list += [ [self.D_src, 'D_src.npy'] ]
|
||||
self.model_filename_list += [ [self.D_dst, 'D_dst.npy'] ]
|
||||
|
||||
|
|
@ -833,23 +831,62 @@ class SAEHDModel(ModelBase):
|
|||
|
||||
n_samples = min(4, self.get_batch_size(), 800 // self.resolution )
|
||||
|
||||
result = []
|
||||
st = []
|
||||
for i in range(n_samples):
|
||||
ar = S[i], SS[i], D[i], DD[i], SD[i]
|
||||
|
||||
st.append ( np.concatenate ( ar, axis=1) )
|
||||
|
||||
result += [ ('SAEHD', np.concatenate (st, axis=0 )), ]
|
||||
|
||||
if self.options['learn_mask']:
|
||||
st_m = []
|
||||
if self.resolution <= 256:
|
||||
result = []
|
||||
|
||||
st = []
|
||||
for i in range(n_samples):
|
||||
ar = S[i]*target_srcm[i], SS[i], D[i]*target_dstm[i], DD[i]*DDM[i], SD[i]*(DDM[i]*SDM[i])
|
||||
st_m.append ( np.concatenate ( ar, axis=1) )
|
||||
ar = S[i], SS[i], D[i], DD[i], SD[i]
|
||||
st.append ( np.concatenate ( ar, axis=1) )
|
||||
result += [ ('SAEHD', np.concatenate (st, axis=0 )), ]
|
||||
|
||||
result += [ ('SAEHD masked', np.concatenate (st_m, axis=0 )), ]
|
||||
if self.options['learn_mask']:
|
||||
st_m = []
|
||||
for i in range(n_samples):
|
||||
ar = S[i]*target_srcm[i], SS[i], D[i]*target_dstm[i], DD[i]*DDM[i], SD[i]*(DDM[i]*SDM[i])
|
||||
st_m.append ( np.concatenate ( ar, axis=1) )
|
||||
|
||||
result += [ ('SAEHD masked', np.concatenate (st_m, axis=0 )), ]
|
||||
else:
|
||||
result = []
|
||||
|
||||
st = []
|
||||
for i in range(n_samples):
|
||||
ar = S[i], SS[i]
|
||||
st.append ( np.concatenate ( ar, axis=1) )
|
||||
result += [ ('SAEHD src-src', np.concatenate (st, axis=0 )), ]
|
||||
|
||||
st = []
|
||||
for i in range(n_samples):
|
||||
ar = D[i], DD[i]
|
||||
st.append ( np.concatenate ( ar, axis=1) )
|
||||
result += [ ('SAEHD dst-dst', np.concatenate (st, axis=0 )), ]
|
||||
|
||||
st = []
|
||||
for i in range(n_samples):
|
||||
ar = D[i], SD[i]
|
||||
st.append ( np.concatenate ( ar, axis=1) )
|
||||
result += [ ('SAEHD pred', np.concatenate (st, axis=0 )), ]
|
||||
|
||||
if self.options['learn_mask']:
|
||||
st_m = []
|
||||
for i in range(n_samples):
|
||||
ar = S[i]*target_srcm[i], SS[i]
|
||||
st_m.append ( np.concatenate ( ar, axis=1) )
|
||||
result += [ ('SAEHD masked src-src', np.concatenate (st_m, axis=0 )), ]
|
||||
|
||||
st_m = []
|
||||
for i in range(n_samples):
|
||||
ar = D[i]*target_dstm[i], DD[i]*DDM[i]
|
||||
st_m.append ( np.concatenate ( ar, axis=1) )
|
||||
result += [ ('SAEHD masked dst-dst', np.concatenate (st_m, axis=0 )), ]
|
||||
|
||||
st_m = []
|
||||
for i in range(n_samples):
|
||||
ar = D[i]*target_dstm[i], SD[i]*(DDM[i]*SDM[i])
|
||||
st_m.append ( np.concatenate ( ar, axis=1) )
|
||||
result += [ ('SAEHD masked pred', np.concatenate (st_m, axis=0 )), ]
|
||||
|
||||
return result
|
||||
|
||||
def predictor_func (self, face=None):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue