unk_token='[UNK]',
pad_token='[PAD]')
tokenizer = JiebaTokenizer(vocab)
label_map = {0: 'dissimilar', 1: 'similar'}
# Constructs the newtork.
model = SimNet(network=args.network,
vocab_size=len(vocab),
num_classes=len(label_map))
# Loads model parameters.
state_dict = paddle.load(args.params_path)
model.set_dict(state_dict)
print("Loaded parameters from %s" % args.params_path)
# Firstly pre-processing prediction data and then do predict.
data = [
['世界上什么东西最小', '世界上什么东西最小？'],
['光眼睛大就好看吗', '眼睛好看吗？'],
['小蝌蚪找妈妈怎么样', '小蝌蚪找妈妈是谁画的'],
]
examples = preprocess_prediction_data(data, tokenizer)
results = predict(model,
examples,
label_map=label_map,
batch_size=args.batch_size,
pad_token_id=vocab.token_to_idx.get('[PAD]', 0))
for idx, text in enumerate(data):
print('Data: {} \t Label: {}'.format(text, results[idx]))
# Loads vocab.
vocab = load_vocab(args.vocab_path)
label_map = {0: 'negative', 1: 'positive'}
# Constructs the newtork.
model = ppnlp.models.Senta(network=args.network,
vocab_size=len(vocab),
num_classes=len(label_map))
# Loads model parameters.
state_dict = paddle.load(args.params_path)
model.set_dict(state_dict)
print("Loaded parameters from %s" % args.params_path)
# Firstly pre-processing prediction data and then do predict.
data = [
'这个宾馆比较陈旧了，特价的房间也很一般。总体来说一般',
'怀着十分激动的心情放映，可是看着看着发现，在放映完毕后，出现一集米老鼠的动画片',
'作为老的四星酒店，房间依然很整洁，相当不错。机场接机服务很好，可以在车上办理入住手续，节省时间。',
]
examples = preprocess_prediction_data(data, vocab)
results = predict(model,
examples,
label_map=label_map,
batch_size=args.batch_size,
collate_fn=generate_batch)
for idx, text in enumerate(data):
print('Data: {} \t Label: {}'.format(text, results[idx]))