def main():
parser = make_parser()
# args and init
args = parser.parse_args()
args.dout = args.dout.format(**vars(args))
torch.manual_seed(args.seed)
# check if dataset has been preprocessed
if not os.path.exists(os.path.join(args.data, "%s.vocab" % args.pp_folder)) and not args.preprocess:
raise Exception("Dataset not processed; run with --preprocess")
# make output dir
pprint.pprint(args)
if not os.path.isdir(args.dout):
os.makedirs(args.dout)
# load train/valid/tests splits
with open(args.splits) as f:
splits = json.load(f)
pprint.pprint({k: len(v) for k, v in splits.items()})
# preprocess and save
if args.preprocess:
print("\nPreprocessing dataset and saving to %s folders ... This will take a while. Do this once as required." % args.pp_folder)
dataset = Dataset(args, None)
dataset.preprocess_splits(splits)
vocab = torch.load(os.path.join(args.dout, "%s.vocab" % args.pp_folder))
else:
vocab = torch.load(os.path.join(args.data, "%s.vocab" % args.pp_folder))
# load model
if args.resume:
print("Loading: " + args.resume)
model, optimizer = Chunker.load(args.resume)
else:
model = Chunker(args, vocab)
optimizer = None
# to gpu
if args.gpu:
model = model.to(torch.device('cuda'))
if not optimizer is None:
optimizer_to(optimizer, torch.device('cuda'))
# start train loop
model.run_train(splits, optimizer=optimizer)
with open(args.splits) as f:
splits = json.load(f)
pprint.pprint({k: len(v) for k, v in splits.items()})
# preprocess and save
if args.preprocess:
print("\nPreprocessing dataset and saving to %s folders ... This will take a while. Do this once as required." % args.pp_folder)
dataset = Dataset(args, None)
dataset.preprocess_splits(splits)
vocab = torch.load(os.path.join(args.dout, "%s.vocab" % args.pp_folder))
else:
vocab = torch.load(os.path.join(args.data, "%s.vocab" % args.pp_folder))
# load model
M = import_module('model.{}'.format(args.model))
if args.resume:
print("Loading: " + args.resume)
model, optimizer = M.Module.load(args.resume)
else:
model = M.Module(args, vocab)
optimizer = None
# to gpu
if args.gpu:
model = model.to(torch.device('cuda'))
if not optimizer is None:
optimizer_to(optimizer, torch.device('cuda'))
# start train loop
model.run_train(splits, optimizer=optimizer)
