def load_dataset(args):
train_dataset = LJspeechDataset(args.data_path, True, 0.1)
test_dataset = LJspeechDataset(args.data_path, False, 0.1)
train_loader = DataLoader(train_dataset, batch_size=args.batch_size, shuffle=True, collate_fn=collate_fn,
num_workers=args.num_workers, pin_memory=True)
test_loader = DataLoader(test_dataset, batch_size=args.batch_size, collate_fn=collate_fn,
num_workers=args.num_workers, pin_memory=True)
synth_loader = DataLoader(test_dataset, batch_size=1, collate_fn=collate_fn_synthesize,
num_workers=args.num_workers, pin_memory=True)
return train_loader, test_loader, synth_loader
def load_dataset(args):
test_dataset = LJspeechDataset(args.data_path, False, 0.1)
synth_loader = DataLoader(test_dataset,
batch_size=1,
collate_fn=collate_fn_synthesize,
num_workers=args.num_workers,
pin_memory=True)
return synth_loader
if not os.path.isdir(args.save):
os.makedirs(args.save)
if not os.path.isdir(args.loss):
os.makedirs(args.loss)
if not os.path.isdir(args.sample_path):
os.makedirs(args.sample_path)
if not os.path.isdir(os.path.join(args.sample_path, args.model_name)):
os.makedirs(os.path.join(args.sample_path, args.model_name))
if not os.path.isdir(os.path.join(args.save, args.model_name)):
os.makedirs(os.path.join(args.save, args.model_name))
use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
# LOAD DATASETS
train_dataset = LJspeechDataset(args.data_path, True, 0.1)
test_dataset = LJspeechDataset(args.data_path, False, 0.1)
train_loader = DataLoader(train_dataset,
batch_size=args.batch_size,
shuffle=True,
collate_fn=collate_fn,
num_workers=args.num_workers,
pin_memory=True)
test_loader = DataLoader(test_dataset,
batch_size=args.batch_size,
collate_fn=collate_fn,
num_workers=args.num_workers,
pin_memory=True)
synth_loader = DataLoader(test_dataset,
batch_size=1,
collate_fn=collate_fn_synthesize,
default=0,
help='Number of workers')
parser.add_argument('--log', type=str, default='./log', help='Log folder.')
args = parser.parse_args()
if not os.path.isdir(args.sample_path):
os.makedirs(args.sample_path)
if not os.path.isdir(os.path.join(args.sample_path, args.model_name)):
os.makedirs(os.path.join(args.sample_path, args.model_name))
use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
# LOAD DATASETS
test_dataset = LJspeechDataset(args.data_path, False, 0.1)
synth_loader = DataLoader(test_dataset,
batch_size=1,
collate_fn=collate_fn_synthesize,
num_workers=args.num_workers,
pin_memory=True)
def build_model():
causality = True if args.causal == 'yes' else False
model = Flowavenet(in_channel=1,
cin_channel=args.cin_channels,
n_block=args.n_block,
n_flow=args.n_flow,
n_layer=args.n_layer,
affine=True,
