def test(args):
tokenizer, vocab2id, id2vocab = bert_tokenizer()
detokenizer = bert_detokenizer()
data_path = os.path.join(args.data_path, args.dataset + '/')
dev_samples = torch.load(os.path.join(data_path, args.dataset + '.dev.pkl'))
if len(dev_samples) > 10:
dev_dataset = GTTPDataset(dev_samples, None, None, None, None, None,None, None, sample_tensor=torch.load(os.path.join(data_path, args.dataset+ '.dev.GTTP.dataset.pkl')))
test_samples = torch.load(os.path.join(data_path, args.dataset + '.test.pkl'))
if len(test_samples) > 10:
test_dataset = GTTPDataset(test_samples, None, None, None, None, None,None, None, sample_tensor=torch.load(os.path.join(data_path, args.dataset+ '.test.GTTP.dataset.pkl')))
for i in range(args.epoch):
print('epoch', i)
file = args.output_path + 'model/' + str(i) + '.pkl'
if os.path.exists(file):
model = GTTP(args.embedding_size, args.hidden_size, vocab2id, id2vocab, max_dec_len=args.max_target_length, beam_width=1)
model.load_state_dict(torch.load(file, map_location='cpu'))
trainer = CumulativeTrainer(model, tokenizer, detokenizer, args.local_rank, args.num_gpu)
if dev_dataset:
predictions=trainer.predict('test', dev_dataset, collate_fn, args.batch_size)
save_result(predictions, dev_dataset, model.to_sentence, detokenizer, args.output_path, args.local_rank, i, args.dataset+'_dev')
if test_dataset:
predictions =trainer.predict('test', test_dataset, collate_fn, args.batch_size)
save_result(predictions, test_dataset, model.to_sentence, detokenizer, args.output_path, args.local_rank, i, args.dataset+'_test')
def test(args):
batch_size = 16
output_path = base_output_path
dataset = args.dataset
data_path = args.data_path + dataset + '/' + dataset
tokenizer, vocab2id, id2vocab = bert_tokenizer()
detokenizer = bert_detokenizer()
marco_dev_samples = torch.load(data_path + 'marco/marco.dev.pkl')
marco_dev_dataset = S2SADataset(
marco_dev_samples,
None,
None,
None,
None,
None,
None,
None,
None,
sample_tensor=torch.load(data_path +
'marco/marco.dev.S2SA.dataset.pkl'))
marco_test_samples = torch.load(data_path + 'marco/marco.test.pkl')
marco_test_dataset = S2SADataset(
marco_test_samples,
None,
None,
None,
None,
None,
None,
None,
None,
sample_tensor=torch.load(data_path +
'marco/marco.test.S2SA.dataset.pkl'))
cast_test_samples = torch.load(data_path + '.pkl')
cast_test_dataset = S2SADataset(
cast_test_samples,
None,
None,
None,
None,
None,
None,
None,
None,
sample_tensor=torch.load(data_path + '.S2SA.dataset.pkl'))
for i in range(epoch):
print('epoch', i)
file = output_path + 'model/' + str(i) + '.pkl'
if os.path.exists(file):
model = S2SA(embedding_size,
hidden_size,
vocab2id,
id2vocab,
max_dec_len=max_target_length,
beam_width=1)
model.load_state_dict(torch.load(file, map_location='cpu'))
trainer = CumulativeTrainer(model, tokenizer, detokenizer,
args.local_rank, 4)
predictions = trainer.predict('test', marco_dev_dataset,
collate_fn, batch_size)
save_result(predictions, marco_dev_dataset, model.to_sentence,
detokenizer, output_path, args.local_rank, i,
'marco_dev')
predictions = trainer.predict('test', marco_test_dataset,
collate_fn, batch_size)
save_result(predictions, marco_test_dataset, model.to_sentence,
detokenizer, output_path, args.local_rank, i,
'marco_test')
predictions = trainer.predict('test', cast_test_dataset,
collate_fn, batch_size)
save_result(predictions, cast_test_dataset, model.to_sentence,
detokenizer, output_path, args.local_rank, i,
'cast_test')
def test(args):
batch_size = args.test_batch_size
ratio = args.profile_dropout_ratio
policy = args.neighbor_policy
task_dir = '%s/%s-%s' % (src, task, policy)
drop_attr = ''
if args.keep_attributes is not None:
for k in _keys:
if k not in args.keep_attributes:
drop_attr += '_%s' % k
_, _, _, kb_vocab = torch.load('%s/kbs.pkl' % task_dir)
candidates = torch.load('%s/candidates.pkl' % task_dir)
candidate_tensor = torch.load('%s/candidate.ctds.pkl' % task_dir)
train_samples = torch.load('%s/train.pkl' % task_dir)
dev_samples = torch.load('%s/dev.pkl' % task_dir)
test_samples = torch.load('%s/test.pkl' % task_dir)
meta_data = torch.load('%s/meta.pkl' % task_dir)
vocab2id, id2vocab = torch.load('%s/vocab.pkl' % task_dir)
tokenizer = babi_tokenizer
print('Item size', len(vocab2id))
train_sample_tensor = torch.load('%s/train.ctds-%s%s.pkl' %
(task_dir, ratio, drop_attr))
dev_sample_tensor = torch.load('%s/dev.ctds-%s%s.pkl' %
(task_dir, ratio, drop_attr))
test_sample_tensor = torch.load('%s/test.ctds-%s%s.pkl' %
(task_dir, ratio, drop_attr))
dev_dataset = CTDSDataset(dev_samples[:cut_data_index],
candidates,
meta_data,
tokenizer,
vocab2id,
id2vocab,
sample_tensor=dev_sample_tensor[:cut_data_index],
train_sample_tensor=train_sample_tensor)
test_dataset = CTDSDataset(
test_samples[:cut_data_index],
candidates,
meta_data,
tokenizer,
vocab2id,
id2vocab,
sample_tensor=test_sample_tensor[:cut_data_index],
train_sample_tensor=train_sample_tensor)
for i in range(args.infer_epoch_start, epoches):
print('epoch', i)
file = os.path.join(output_model_path, str(i) + '.pkl')
if os.path.exists(file):
model = CTDS(hidden_size, vocab2id, id2vocab, candidate_tensor,
meta_data)
model.load_state_dict(torch.load(file, map_location='cpu'))
model_trainer = CumulativeTrainer(
model,
tokenizer,
None,
args.local_rank,
4,
accumulation_steps=accumulation_steps,
max_grad_norm=args.max_grad_norm,
save_data_attributes=save_data_attributes)
# Dev infer # dev_list_output[0][1].tolist()
dev_list_output = model_trainer.predict('infer', dev_dataset,
collate_fn, batch_size)
#save result, note each GPU process will save a separate file
# save_dev = [[batch_data[0][0], batch_data[0][1], batch_data[0][2], batch_data[1][0], batch_data[1][1]] for batch_data in dev_list_output]
# save_dev = [[batch_data[0]['response_id'], batch_data[1]] for batch_data in dev_list_output]
torch.save(
dev_list_output,
os.path.join(output_result_path,
'dev.%s.%s' % (i, args.local_rank)))
# Test infer
test_list_output = model_trainer.predict('infer', test_dataset,
collate_fn, batch_size)
# save_test = [[batch_data[0][0], batch_data[0][1], batch_data[1][0], batch_data[1][1]] for batch_data in test_list_output]
# save_test = [[batch_data[0]['response_id'], batch_data[1]] for batch_data in test_list_output]
torch.save(
test_list_output,
os.path.join(output_result_path,
'test.%s.%s' % (i, args.local_rank)))