def cli_main():
"""
MODIFIED: task defaults to gec
"""
parser = options.get_generation_parser(default_task='gec')
args = options.parse_args_and_arch(parser)
main(args)
def generate_main(data_dir, extra_flags=None):
generate_parser = options.get_generation_parser()
generate_args = options.parse_args_and_arch(
generate_parser,
[
data_dir,
'--path',
os.path.join(data_dir, 'checkpoint_last.pt'),
'--beam',
'3',
'--batch-size',
'64',
'--max-len-b',
'5',
'--gen-subset',
'valid',
'--no-progress-bar',
'--print-alignment',
] + (extra_flags or []),
)
# evaluate model in batch mode
generate.main(generate_args)
# evaluate model interactively
generate_args.buffer_size = 0
generate_args.input = '-'
generate_args.max_sentences = None
orig_stdin = sys.stdin
sys.stdin = StringIO('h e l l o\n')
interactive.main(generate_args)
sys.stdin = orig_stdin
def train_translation_model(data_dir, arch, extra_flags=None):
train_parser = options.get_training_parser()
train_args = options.parse_args_and_arch(
train_parser,
[
'--task',
'translation',
data_dir,
'--save-dir',
data_dir,
'--arch',
arch,
'--optimizer',
'nag',
'--lr',
'0.05',
'--max-tokens',
'500',
'--max-epoch',
'1',
'--no-progress-bar',
'--distributed-world-size',
'1',
'--source-lang',
'in',
'--target-lang',
'out',
] + (extra_flags or []),
)
train.main(train_args)
def cli_main():
parser = options.get_training_parser()
args = options.parse_args_and_arch(parser)
if args.distributed_init_method is None:
distributed_utils.infer_init_method(args)
if args.distributed_init_method is not None:
# distributed training
distributed_main(args.device_id, args)
elif args.distributed_world_size > 1:
# fallback for single node with multiple GPUs
port = random.randint(10000, 20000)
args.distributed_init_method = 'tcp://localhost:{port}'.format(port=port)
args.distributed_rank = None # set based on device id
if max(args.update_freq) > 1 and args.ddp_backend != 'no_c10d':
print('| NOTE: you may get better performance with: --ddp-backend=no_c10d')
torch.multiprocessing.spawn(
fn=distributed_main,
args=(args, ),
nprocs=args.distributed_world_size,
)
else:
# single GPU training
main(args)
def eval_lm_main(data_dir):
eval_lm_parser = options.get_eval_lm_parser()
eval_lm_args = options.parse_args_and_arch(
eval_lm_parser,
[
data_dir,
'--path',
os.path.join(data_dir, 'checkpoint_last.pt'),
'--no-progress-bar',
],
)
eval_lm.main(eval_lm_args)
def train_language_model(data_dir, arch):
train_parser = options.get_training_parser()
train_args = options.parse_args_and_arch(
train_parser,
[
'--task',
'language_modeling',
data_dir,
'--arch',
arch,
'--optimizer',
'nag',
'--lr',
'0.1',
'--criterion',
'adaptive_loss',
'--adaptive-softmax-cutoff',
'5,10,15',
'--decoder-layers',
'[(850, 3)] * 2 + [(1024,4)]',
'--decoder-embed-dim',
'280',
'--max-tokens',
'500',
'--tokens-per-sample',
'500',
'--save-dir',
data_dir,
'--max-epoch',
'1',
'--no-progress-bar',
'--distributed-world-size',
'1',
'--ddp-backend',
'no_c10d',
],
)
train.main(train_args)
def cli_main():
parser = options.get_eval_lm_parser()
args = options.parse_args_and_arch(parser)
main(args)
def cli_main():
parser = options.get_generation_parser(interactive=True)
args = options.parse_args_and_arch(parser)
main(args)
def cli_main():
parser = options.get_generation_parser()
args = options.parse_args_and_arch(parser)
main(args)
def cli_main():
parser = get_lm_scorer_parser()
args = options.parse_args_and_arch(parser)
main(args)