def main():
parser = argparse.ArgumentParser()
# general configuration
parser.add_argument('--ngpu', default=0, type=int,
help='Number of GPUs')
parser.add_argument('--backend', default='chainer', type=str,
choices=['chainer', 'pytorch'],
help='Backend library')
parser.add_argument('--outdir', type=str, required=True,
help='Output directory')
parser.add_argument('--debugmode', default=1, type=int,
help='Debugmode')
parser.add_argument('--dict', type=str, required=True,
help='Dictionary')
parser.add_argument('--seed', default=1, type=int,
help='Random seed')
parser.add_argument('--minibatches', '-N', type=int, default='-1',
help='Process only N minibatches (for debug)')
parser.add_argument('--verbose', '-V', default=0, type=int,
help='Verbose option')
# task related
parser.add_argument('--train-label', type=str, required=True,
help='Filename of train label data')
parser.add_argument('--valid-label', type=str, required=True,
help='Filename of validation label data')
# LSTMLM training configuration
parser.add_argument('--batchsize', '-b', type=int, default=2048,
help='Number of examples in each mini-batch')
parser.add_argument('--bproplen', '-l', type=int, default=35,
help='Number of words in each mini-batch '
'(= length of truncated BPTT)')
parser.add_argument('--epoch', '-e', type=int, default=20,
help='Number of sweeps over the dataset to train')
parser.add_argument('--gradclip', '-c', type=float, default=5,
help='Gradient norm threshold to clip')
parser.add_argument('--unit', '-u', type=int, default=650,
help='Number of LSTM units in each layer')
args = parser.parse_args()
# logging info
if args.verbose > 0:
logging.basicConfig(
level=logging.INFO, format='%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s')
else:
logging.basicConfig(
level=logging.WARN, format='%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s')
logging.warning('Skip DEBUG/INFO messages')
# check CUDA_VISIBLE_DEVICES
if args.ngpu > 0:
# python 2 case
if platform.python_version_tuple()[0] == '2':
if "clsp.jhu.edu" in subprocess.check_output(["hostname", "-f"]):
cvd = subprocess.check_output(["/usr/local/bin/free-gpu", "-n", str(args.ngpu)]).strip()
logging.info('CLSP: use gpu' + cvd)
os.environ['CUDA_VISIBLE_DEVICES'] = cvd
else:
if "clsp.jhu.edu" in subprocess.check_output(["hostname", "-f"]).decode():
cvd = subprocess.check_output(["/usr/local/bin/free-gpu", "-n", str(args.ngpu)]).decode().strip()
logging.info('CLSP: use gpu' + cvd)
os.environ['CUDA_VISIBLE_DEVICES'] = cvd
cvd = os.environ.get("CUDA_VISIBLE_DEVICES")
if cvd is None:
logging.warn("CUDA_VISIBLE_DEVICES is not set.")
elif args.ngpu != len(cvd.split(",")):
logging.error("#gpus is not matched with CUDA_VISIBLE_DEVICES.")
sys.exit(1)
# display PYTHONPATH
logging.info('python path = ' + os.environ['PYTHONPATH'])
# seed setting
nseed = args.seed
random.seed(nseed)
np.random.seed(nseed)
# load dictionary
with open(args.dict, 'rb') as f:
dictionary = f.readlines()
char_list = [entry.decode('utf-8').split(' ')[0] for entry in dictionary]
char_list.insert(0, '<blank>')
char_list.append('<eos>')
args.char_list_dict = {x: i for i, x in enumerate(char_list)}
args.n_vocab = len(char_list)
# train
logging.info('backend = ' + args.backend)
if args.backend == "chainer":
from lm_chainer import train
train(args)
elif args.backend == "pytorch":
from lm_pytorch import train
train(args)
else:
raise ValueError("chainer and pytorch are only supported.")
def main():
parser = argparse.ArgumentParser()
# general configuration
parser.add_argument('--gpu',
'-g',
default='-1',
type=int,
help='GPU ID (negative value indicates CPU)')
parser.add_argument('--backend',
default='chainer',
type=str,
choices=['chainer', 'pytorch'],
help='Backend library')
parser.add_argument('--outdir',
type=str,
required=True,
help='Output directory')
parser.add_argument('--debugmode', default=1, type=int, help='Debugmode')
parser.add_argument('--dict', type=str, required=True, help='Dictionary')
parser.add_argument('--seed', default=1, type=int, help='Random seed')
parser.add_argument('--minibatches',
'-N',
type=int,
default='-1',
help='Process only N minibatches (for debug)')
parser.add_argument('--verbose',
'-V',
default=0,
type=int,
help='Verbose option')
# task related
parser.add_argument('--train-label',
type=str,
required=True,
help='Filename of train label data (json)')
parser.add_argument('--valid-label',
type=str,
required=True,
help='Filename of validation label data (json)')
# LSTMLM training configuration
parser.add_argument('--batchsize',
'-b',
type=int,
default=2048,
help='Number of examples in each mini-batch')
parser.add_argument('--bproplen',
'-l',
type=int,
default=35,
help='Number of words in each mini-batch '
'(= length of truncated BPTT)')
parser.add_argument('--epoch',
'-e',
type=int,
default=20,
help='Number of sweeps over the dataset to train')
parser.add_argument('--gradclip',
'-c',
type=float,
default=5,
help='Gradient norm threshold to clip')
parser.add_argument('--unit',
'-u',
type=int,
default=650,
help='Number of LSTM units in each layer')
args = parser.parse_args()
# logging info
if args.verbose > 0:
logging.basicConfig(
level=logging.INFO,
format=
'%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s')
else:
logging.basicConfig(
level=logging.WARN,
format=
'%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s')
logging.warning('Skip DEBUG/INFO messages')
# display PYTHONPATH
logging.info('python path = ' + os.environ['PYTHONPATH'])
# seed setting
nseed = args.seed
random.seed(nseed)
np.random.seed(nseed)
# load dictionary
with open(args.dict, 'rb') as f:
dictionary = f.readlines()
char_list = [entry.decode('utf-8').split(' ')[0] for entry in dictionary]
char_list.insert(0, '<blank>')
char_list.append('<eos>')
args.char_list_dict = {x: i for i, x in enumerate(char_list)}
args.n_vocab = len(char_list)
# train
logging.info('backend = ' + args.backend)
if args.backend == "chainer":
from lm_chainer import train
train(args)
elif args.backend == "pytorch":
from lm_pytorch import train
train(args)
else:
raise ValueError("chainer and pytorch are only supported.")