def train_siamese():
# 读取配置
# conf = Config()
cfg_path = "./configs/config.yml"
cfg = yaml.load(open(cfg_path, encoding='utf-8'), Loader=yaml.FullLoader)
# 读取数据
data_train, data_val, data_test = data_input.get_lcqmc()
# data_train = data_train[:100]
print("train size:{},val size:{}, test size:{}".format(
len(data_train), len(data_val), len(data_test)))
model = SiamenseRNN(cfg)
model.fit(data_train, data_val, data_test)
pass
test_acc = accuracy_score(val_label, val_pred)
return test_acc
def predict(self, test_data):
pbar = data_input.get_batch(test_data,
batch_size=self.cfg['batch_size'],
is_test=1)
val_pred, val_prob = [], []
for (t1_ids, t1_len, t2_ids, t2_len) in pbar:
fd = self.feed_batch(t1_ids, t1_len, t2_ids, t2_len, is_test=1)
pred_labels, pred_prob = self.sess.run(
[self.predict_idx, self.predict_prob], feed_dict=fd)
val_pred.extend(pred_labels)
val_prob.extend(pred_prob)
return val_pred, val_prob
if __name__ == "__main__":
start = time.time()
# 读取配置
conf = Config()
# 读取数据
dataset = hub.dataset.LCQMC()
data_train, data_val, data_test = data_input.get_lcqmc()
# data_train = data_train[:10000]
print("train size:{},val size:{}, test size:{}".format(
len(data_train), len(data_val), len(data_test)))
model = SiamenseRNN(conf)
model.fit(data_train, data_val, data_test)
pass