def main():
print('Initializing Training Process..')
parser = argparse.ArgumentParser()
parser.add_argument('--group_name', default=None)
parser.add_argument('--checkpoint_path', default='cp_hifigan')
parser.add_argument('--config', default='config_8k.json')
parser.add_argument('--training_epochs', default=3100, type=int)
parser.add_argument('--stdout_interval', default=5, type=int)
parser.add_argument('--checkpoint_interval', default=5000, type=int)
parser.add_argument('--summary_interval', default=100, type=int)
parser.add_argument('--validation_interval', default=1000, type=int)
parser.add_argument('--fine_tuning', default=False, type=bool)
a = parser.parse_args()
with open(a.config) as f:
data = f.read()
json_config = json.loads(data)
h = AttrDict(json_config)
build_env(a.config, 'config.json', a.checkpoint_path)
model = Generator(h)
inputs = torch.randn(10, 80, 80)
output = model(inputs)
print(output.shape)
def main():
print('Initializing Training Process..')
parser = argparse.ArgumentParser()
parser.add_argument('--group_name', default=None)
parser.add_argument('--input_wavs_dir',
default='LJSpeech-1.1/wavs',
help='')
parser.add_argument('--input_mels_dir', default='ft_dataset', help='')
parser.add_argument('--input_training_file',
default='LJSpeech-1.1/training.txt',
help='')
parser.add_argument('--input_validation_file',
default='LJSpeech-1.1/validation.txt',
help='')
parser.add_argument('--checkpoint_path', default='cp_hifigan')
parser.add_argument('--config', default='')
parser.add_argument('--training_epochs', default=3100, type=int)
parser.add_argument('--stdout_interval', default=5, type=int)
parser.add_argument('--checkpoint_interval', default=5000, type=int)
parser.add_argument('--summary_interval', default=100, type=int)
parser.add_argument('--validation_interval', default=1000, type=int)
parser.add_argument('--fine_tuning', default=False, type=bool)
a = parser.parse_args()
with open(a.config) as f:
data = f.read()
json_config = json.loads(data)
h = AttrDict(json_config)
build_env(a.config, 'config.json', a.checkpoint_path)
torch.manual_seed(h.seed)
if torch.cuda.is_available():
torch.cuda.manual_seed(h.seed)
h.num_gpus = torch.cuda.device_count()
h.batch_size = int(h.batch_size / h.num_gpus)
print('Batch size per GPU :', h.batch_size)
else:
pass
if h.num_gpus > 1:
mp.spawn(train, nprocs=h.num_gpus, args=(
a,
h,
))
else:
train(0, a, h)
def launch(
executable, arguments=None, env_configs=None, from_current_env=True,
keys_to_remove=None, dry=False):
# Build command line:
if is_string(arguments):
arguments = shlex.split(arguments)
elif arguments is None:
arguments = []
command = [executable] + arguments
# Build env:
env = build_env(
env_configs, from_current_env=from_current_env,
keys_to_remove=keys_to_remove, override_warnings=True, verbose=dry)
# Launch:
if dry:
return
try:
if PLATFORM == 'linux':
subprocess.call(command, env=env)
else:
if any(s in executable for s in ('cmd', 'powershell', 'pwsh')):
subprocess.call(command, env=env, shell=True)
else:
subprocess.Popen(command, env=env)
except TypeError:
pprint.pprint(env)
raise
except FileNotFoundError:
print('Failed to launch following command:')
print(command)
print('PATH =', env['PATH'].split(os.pathsep))
raise
def main():
print('Initializing the Training Process..')
parser = argparse.ArgumentParser()
parser.add_argument('--input_wavs_dir', default='data/recordings')
parser.add_argument('--input_mels_dir', default='processed_spokenDigits_np')
parser.add_argument('--config', default='processed_spokenDigits_np')
parser.add_argument('--training_epochs', default='1000')
a = parser.parse_args()
with open(a.config) as f:
data = f.read()
json_config = json.loads(data)
h = AttrDict(json_config)
build_env(a.config, 'config.json', a.checkpoint_path)
torch.manual_seed(h.seed):
if torch.cuda.is_availale(h.seed):
torch.cuda.manual_seeed(h.seed)
h.batch_size = int(h.batch_size / h.num_gpu)
else:
print('\nRunning on cpu')
# train now--
g_losses, d_losses, generated_mels = train(h)
# visualize the loss as the network trained
plt.plot(g_losses, d_losses)
plt.xlabel('100\'s of batches')
plt.ylabel('loss')
plt.grid(True)
# plt.ylim(0, 2.5) # consistent scale
plt.show()
def main():
print('Initializing Training Process..')
parser = argparse.ArgumentParser()
parser.add_argument('--rank', default=0, type=int)
parser.add_argument('--group_name', default=None)
parser.add_argument('--input_wavs_dir', default='data/LJSpeech-1.1/wavs')
parser.add_argument('--input_train_metafile', default='data/LJSpeech-1.1/metadata_ljspeech.csv')
parser.add_argument('--input_valid_metafile', default='data/LJSpeech-1.1/metadata_test_ljspeech.csv')
parser.add_argument('--inference', default=False, action='store_true')
parser.add_argument('--cps', default='cp_melgan')
parser.add_argument('--cp_g', default='') # ex) cp_mgt_01/g_100.pth
parser.add_argument('--cp_d', default='') # ex) cp_mgt_01/d_100.pth
parser.add_argument('--config', default='hparams.json')
parser.add_argument('--training_epochs', default=5000, type=int)
parser.add_argument('--stdout_interval', default=1, type=int)
parser.add_argument('--checkpoint_interval', default=5000, type=int)
parser.add_argument('--summary_interval', default=100, type=int)
parser.add_argument('--validation_interval', default=1000, type=int)
a = parser.parse_args()
with open(a.config) as f:
data = f.read()
global h
json_config = json.loads(data)
h = AttrDict(json_config)
build_env(a.config, 'config.json', a.cps)
torch.manual_seed(h.seed)
global device
if torch.cuda.is_available():
torch.cuda.manual_seed(h.seed)
device = torch.device('cuda')
h.num_gpus = torch.cuda.device_count()
else:
device = torch.device('cpu')
fit(a, a.training_epochs)
import os
from common.argparser import args
from env import build_env
from models.a2c.a2c import learn
if __name__ == '__main__':
env = build_env(
n_vertices=args.n_vertices,
n_edges=args.n_edges,
n_actions=args.n_actions
)
d_model, a_model = learn(
env=env,
defender=args.d_model,
attacker=args.a_model,
seed=args.seed,
nsteps=args.batchsize,
total_epoches=args.total_epoches,
vf_coef=args.vf_coef,
ent_coef=args.ent_coef,
max_grad_norm=args.max_grad_norm,
lr=args.lr,
gamma=args.gamma,
d_load_path=os.path.join('logs', args.d_load, 'd_model.ckpt') if args.d_load else None,
a_load_path=os.path.join('logs', args.a_load, 'a_model.ckpt') if args.a_load else None,
d_save_path=os.path.join('logs', args.note, 'd_model.ckpt'),
a_save_path=os.path.join('logs', args.note, 'a_model.ckpt'),
)