config.words_num = len(train_iter.dataset.TEXT_FIELD.vocab)
print('Dataset {} Mode {}'.format(args.dataset, args.mode))
print('VOCAB num',len(train_iter.dataset.TEXT_FIELD.vocab))
print('LABEL.target_class:', train_iter.dataset.NUM_CLASSES)
print('Train instance', len(train_iter.dataset))
print('Dev instance', len(dev_iter.dataset))
print('Test instance', len(test_iter.dataset))
if args.resume_snapshot:
if args.cuda:
model = torch.load(args.resume_snapshot, map_location=lambda storage, location: storage.cuda(args.gpu))
else:
model = torch.load(args.resume_snapshot, map_location=lambda storage, location: storage)
else:
model = KimCNN(config)
if args.cuda:
model.cuda()
print('Shift model to GPU')
parameter = filter(lambda p: p.requires_grad, model.parameters())
optimizer = torch.optim.Adadelta(parameter, lr=args.lr, weight_decay=args.weight_decay)
if args.dataset == 'SST-1':
train_evaluator = EvaluatorFactory.get_evaluator(SST1, model, None, train_iter, args.batch_size, args.gpu)
test_evaluator = EvaluatorFactory.get_evaluator(SST1, model, None, test_iter, args.batch_size, args.gpu)
dev_evaluator = EvaluatorFactory.get_evaluator(SST1, model, None, dev_iter, args.batch_size, args.gpu)
elif args.dataset == 'SST-2':
train_evaluator = EvaluatorFactory.get_evaluator(SST2, model, None, train_iter, args.batch_size, args.gpu)
test_evaluator = EvaluatorFactory.get_evaluator(SST2, model, None, test_iter, args.batch_size, args.gpu)
dev_evaluator = EvaluatorFactory.get_evaluator(SST2, model, None, dev_iter, args.batch_size, args.gpu)
print('VOCAB num', len(train_iter.dataset.TEXT_FIELD.vocab))
print('LABEL.target_class:', train_iter.dataset.NUM_CLASSES)
print('Train instance', len(train_iter.dataset))
print('Dev instance', len(dev_iter.dataset))
print('Test instance', len(test_iter.dataset))
if args.resume_snapshot:
if args.cuda:
model = torch.load(
args.resume_snapshot,
map_location=lambda storage, location: storage.cuda(args.gpu))
else:
model = torch.load(args.resume_snapshot,
map_location=lambda storage, location: storage)
else:
model = KimCNN(config)
if args.cuda:
model.cuda()
print('Shift model to GPU')
parameter = filter(lambda p: p.requires_grad, model.parameters())
optimizer = torch.optim.Adam(parameter,
lr=args.lr,
weight_decay=args.weight_decay)
if args.dataset not in dataset_map:
raise ValueError('Unrecognized dataset')
else:
train_evaluator = EvaluatorFactory.get_evaluator(
dataset_map[args.dataset], model, None, train_iter,
args.batch_size, args.gpu)