def process_train(arguments):
os_utils.set_process_lowest_prio()
args = {
'training_data_src_dir':
arguments.training_data_src_dir,
'training_data_dst_dir':
arguments.training_data_dst_dir,
'pretraining_data_dir':
arguments.pretraining_data_dir,
'model_path':
arguments.model_dir,
'model_name':
arguments.model_name,
'no_preview':
arguments.no_preview,
'debug':
arguments.debug,
'execute_programs':
[[int(x[0]), x[1]] for x in arguments.execute_program]
}
device_args = {
'cpu_only': arguments.cpu_only,
'force_gpu_idx': arguments.force_gpu_idx,
}
from mainscripts import Trainer
Trainer.main(args, device_args)
def process_train(arguments):
if 'DFL_TARGET_EPOCH' in os.environ.keys():
arguments.target_epoch = int ( os.environ['DFL_TARGET_EPOCH'] )
if 'DFL_BATCH_SIZE' in os.environ.keys():
arguments.batch_size = int ( os.environ['DFL_BATCH_SIZE'] )
from mainscripts import Trainer
Trainer.main (
training_data_src_dir=arguments.training_data_src_dir,
training_data_dst_dir=arguments.training_data_dst_dir,
model_path=arguments.model_dir,
model_name=arguments.model_name,
debug = arguments.debug,
#**options
batch_size = arguments.batch_size,
write_preview_history = arguments.write_preview_history,
target_epoch = arguments.target_epoch,
save_interval_min = arguments.save_interval_min,
choose_worst_gpu = arguments.choose_worst_gpu,
force_best_gpu_idx = arguments.force_best_gpu_idx,
multi_gpu = arguments.multi_gpu,
force_gpu_idxs = arguments.force_gpu_idxs,
cpu_only = arguments.cpu_only
)
def process_train(arguments):
osex.set_process_lowest_prio()
kwargs = {
'model_class_name':
arguments.model_name,
'saved_models_path':
Path(arguments.model_dir),
'training_data_src_path':
Path(arguments.training_data_src_dir),
'training_data_dst_path':
Path(arguments.training_data_dst_dir),
'pretraining_data_path':
Path(arguments.pretraining_data_dir)
if arguments.pretraining_data_dir is not None else None,
'pretrained_model_path':
Path(arguments.pretrained_model_dir)
if arguments.pretrained_model_dir is not None else None,
'no_preview':
arguments.no_preview,
'force_model_name':
arguments.force_model_name,
'force_gpu_idxs':
[int(x) for x in arguments.force_gpu_idxs.split(',')]
if arguments.force_gpu_idxs is not None else None,
'cpu_only':
arguments.cpu_only,
'execute_programs':
[[int(x[0]), x[1]] for x in arguments.execute_program],
'debug':
arguments.debug,
}
from mainscripts import Trainer
Trainer.main(**kwargs)
def SPTrainLab(context):
args = context.args
if args.pretrainedModelDir:
modelList = get_all_files(args.pretrainedModelDir)
for i in modelList:
shutil.copy(i, os.path.join(args.modelDir, os.path.split(i)[1]))
training_args = {
"training_data_src_dir": args.trainingDataSrcDir,
"training_data_dst_dir": args.trainingDataDstDir,
"pretraining_data_dir": args.pretrainingDataDir,
"model_path": args.modelDir,
"model_name": args.modelName,
"no_preview": True,
"debug": False,
"execute_programs": [],
}
device_args = {"cpu_only": args.cpuOnly, "force_gpu_idx": args.forceGpuIdx}
if not args.__edit:
os.environ["SP_FaceLab_Edit"] = "False"
os.environ["SP_FaceLab_Iterations"] = str(args.iterations)
os.environ["SP_FaceLab_Batch_Size"] = str(args.batchSize)
from mainscripts import Trainer
Trainer.main(training_args, device_args)
for p in multiprocessing.active_children():
if p != multiprocessing.current_process():
p.kill()
return args.modelDir
def process_train(arguments):
osex.set_process_lowest_prio()
kwargs = {
'model_class_name':
arguments.model_name,
'saved_models_path':
Path(arguments.model_dir),
'training_data_src_path':
Path(arguments.training_data_src_dir),
'training_data_dst_path':
Path(arguments.training_data_dst_dir),
'pretraining_data_path':
Path(arguments.pretraining_data_dir)
if arguments.pretraining_data_dir is not None else None,
'pretrained_model_path':
Path(arguments.pretrained_model_dir)
if arguments.pretrained_model_dir is not None else None,
'no_preview':
arguments.no_preview,
'force_model_name':
arguments.force_model_name,
'force_gpu_idxs':
[int(x) for x in arguments.force_gpu_idxs.split(',')]
if arguments.force_gpu_idxs is not None else None,
'cpu_only':
arguments.cpu_only,
'silent_start':
arguments.silent_start,
'execute_programs':
[[int(x[0]), x[1]] for x in arguments.execute_program],
'debug':
arguments.debug,
'use_amp':
arguments.use_amp,
'opt':
arguments.opt,
'lr':
arguments.lr,
'decay_step':
arguments.decay_step,
'config_file':
arguments.config_file,
'bs_per_gpu':
arguments.bs_per_gpu,
}
if arguments.api == 'dfl':
from mainscripts import Trainer
Trainer.main(**kwargs)
elif arguments.api == 'tf1':
from mainscripts import Trainer_tf1
Trainer_tf1.main(**kwargs)
else:
print('Training API {} is invalid'.format(arguments.api))
exit(0)
def process_train(arguments):
from mainscripts import Trainer
Trainer.main(
training_data_src_dir=arguments.training_data_src_dir,
training_data_dst_dir=arguments.training_data_dst_dir,
model_path=arguments.model_dir,
model_name=arguments.model_name,
debug=arguments.debug,
#**options
force_gpu_idx=arguments.force_gpu_idx,
cpu_only=arguments.cpu_only)
def process_train(arguments):
args = {'training_data_src_dir' : arguments.training_data_src_dir,
'training_data_dst_dir' : arguments.training_data_dst_dir,
'model_path' : arguments.model_dir,
'model_name' : arguments.model_name,
'no_preview' : arguments.no_preview,
'debug' : arguments.debug,
}
device_args = {'cpu_only' : arguments.cpu_only,
'force_gpu_idx' : arguments.force_gpu_idx,
}
from mainscripts import Trainer
Trainer.main(args, device_args)
def process_train(arguments):
from mainscripts import Trainer
Trainer.main(
training_data_src_dir=arguments.training_data_src_dir,
training_data_dst_dir=arguments.training_data_dst_dir,
model_path=arguments.model_dir,
model_name=arguments.model_name,
debug=arguments.debug,
#**options
batch_size=arguments.batch_size,
write_preview_history=arguments.write_preview_history,
target_epoch=arguments.target_epoch,
save_interval_min=arguments.save_interval_min,
force_best_gpu_idx=arguments.force_best_gpu_idx,
multi_gpu=arguments.multi_gpu)
def process_train(arguments):
if 'DFL_TARGET_EPOCH' in os.environ.keys():
arguments.session_target_epoch = int(
os.environ['DFL_TARGET_EPOCH'])
if 'DFL_BATCH_SIZE' in os.environ.keys():
arguments.batch_size = int(os.environ['DFL_BATCH_SIZE'])
if 'DFL_WORST_GPU' in os.environ.keys():
arguments.choose_worst_gpu = True
from mainscripts import Trainer
Trainer.main(
training_data_src_dir=arguments.training_data_src_dir,
training_data_dst_dir=arguments.training_data_dst_dir,
model_path=arguments.model_dir,
model_name=arguments.model_name,
debug=arguments.debug,
#**options
choose_worst_gpu=arguments.choose_worst_gpu,
force_best_gpu_idx=arguments.force_best_gpu_idx,
force_gpu_idxs=arguments.force_gpu_idxs,
cpu_only=arguments.cpu_only)
