###############################################################################
# Load data
###############################################################################
# load train and dev dataset
train_corpus = data.Corpus(args.tokenize)
dev_corpus = data.Corpus(args.tokenize)
test_corpus = data.Corpus(args.tokenize)
task_names = ['snli', 'multinli'] if args.task == 'allnli' else [args.task]
for task in task_names:
if 'IMDB' in task:
###############################################################################
# Load Learning to Skim paper's Pickle file
###############################################################################
train_d, dev_d, test_d = helper.get_splited_imdb_data(
args.output_base_path + 'IMDB/' + 'imdb.p', SAG=args.SAG)
train_corpus.parse(train_d, task, args.max_example)
dev_corpus.parse(dev_d, task, args.max_example)
test_corpus.parse(test_d, task, args.max_example)
else:
train_corpus.parse(args.data + task + '/train.txt', task,
args.max_example)
if task == 'multinli':
dev_corpus.parse(args.data + task + '/dev_matched.txt', task,
args.tokenize)
test_corpus.parse(args.data + task + '/test_matched.txt', task,
args.tokenize)
else:
dev_corpus.parse(args.data + task + '/dev.txt', task,
args.tokenize)
test_corpus.parse(args.data + task + '/test.txt', task,
if args.cuda:
torch.cuda.set_device(args.gpu)
model = model.cuda()
print('loading model')
helper.load_model(model, model_path, 'state_dict', args.cuda)
print('vocabulary size = ', len(dictionary))
task_names = ['snli', 'multinli'] if args.task == 'allnli' else [args.task]
for task in task_names:
test_corpus = data.Corpus(args.tokenize)
if 'IMDB' in args.task:
###############################################################################
# Load Learning to Skim paper's Pickle file
###############################################################################
train_d, dev_d, test_d = helper.get_splited_imdb_data(args.output_base_path+task+'/'+'imdb.p')
test_corpus.parse(test_d, task, args.max_example)
# test_corpus.parse(args.output_base_path + task + '/' + args.test + '.txt', 'RT', args.max_example) #although IMDB but selected text saved by budget model from theano in 'RT' format
elif task == 'multinli' and args.test != 'train':
for partition in ['_matched', '_mismatched']:
test_corpus.parse(args.data + task + '/' + args.test + partition + '.txt', task, args.max_example)
print('[' + partition[1:] + '] dataset size = ', len(test_corpus.data))
test_batches = helper.batchify(test_corpus.data, args.eval_batch_size)
if args.test == 'test':
evaluate(model, test_batches, dictionary, args.save_path + args.task + partition + '.csv')
else:
test_accuracy, test_f1 = evaluate(model, test_batches, dictionary)
print('[' + partition[1:] + '] accuracy: %.2f%%' % test_accuracy)
print('[' + partition[1:] + '] f1: %.2f%%' % test_f1)
model = BCN(dictionary, embeddings_index, class_distributions, args)
if args.cuda and torch.cuda.is_available():
torch.cuda.set_device(args.gpu)
model = model.cuda()
helper.load_model_states_from_checkpoint(
model, args.save_path + 'model_best.pth.tar', 'state_dict', args.cuda)
print('vocabulary size = ', len(dictionary))
task_names = ['snli', 'multinli'] if args.task == 'allnli' else [args.task]
for task in task_names:
test_corpus = data.Corpus(args.tokenize)
if 'imdb' in args.task:
###############################################################################
# Load Learning to Skim paper's Pickle file
###############################################################################
train_d, dev_d, test_d = helper.get_splited_imdb_data(
args.save_path + 'data/' + 'imdb.p')
test_corpus.parse(test_d, task, args.max_example)
elif task == 'multinli' and args.test != 'train':
for partition in ['_matched', '_mismatched']:
test_corpus.parse(
args.data + task + '/' + args.test + partition + '.txt',
task, args.max_example)
print('[' + partition[1:] + '] dataset size = ',
len(test_corpus.data))
test_batches = helper.batchify(test_corpus.data,
args.batch_size)
if args.test == 'test':
evaluate(model, test_batches, dictionary,
args.save_path + args.task + partition + '.csv')
else:
###############################################################################
# load train and dev dataset
train_corpus = data.Corpus(args.tokenize)
train_corpus_temp = data.Corpus(args.tokenize)
dev_corpus = data.Corpus(args.tokenize)
test_corpus = data.Corpus(args.tokenize)
ori_train_size = -1
task_names = ['snli', 'multinli'] if args.task == 'allnli' else [args.task]
for task in task_names:
if 'IMDB' in task:
###############################################################################
# Load Learning to Skim paper's Pickle file
###############################################################################
train_d, dev_d, test_d = helper.get_splited_imdb_data(
args.output_base_path + task + '/' + 'imdb.p', SAG=args.SAG)
train_corpus_temp.parse(train_d, task, args.max_example)
dev_corpus.parse(dev_d, task, args.max_example)
test_corpus.parse(test_d, task, args.max_example)
ori_train_size = len(train_corpus_temp.data)
else:
train_corpus_temp.parse(args.output_base_path + task + '/train.txt',
task, args.max_example)
ori_train_size = len(train_corpus_temp.data)
if task == 'multinli':
dev_corpus.parse(args.output_base_path + task + '/dev_matched.txt',
task, args.tokenize)
test_corpus.parse(
args.output_base_path + task + '/test_matched.txt', task,
args.tokenize)