X2.append(iclasses[label])
labels.append(0)
categoricals = {"匹配":1, "不匹配":0}
return X1, X2, labels, categoricals
X1, X2, y, classes = convert_to_pairs(X, y, classes)
X1_train = X1[:-1000]
X2_train = X2[:-1000]
y_train = y[:-1000]
X1_test = X1[-1000:]
X2_test = X2[-1000:]
y_test = y[-1000:]
num_classes = len(classes)
tokenizer = SimpleTokenizer()
tokenizer.fit(X1 + X2)
X1_train = tokenizer.transform(X1_train)
X2_train = tokenizer.transform(X2_train)
maxlen = 48
hdims = 128
epochs = 2
X1_train = sequence.pad_sequences(
X1_train,
maxlen=maxlen,
dtype="int32",
padding="post",
truncating="post",
value=0
from dataset import load_THUCNews_title_label
from dataset import load_weibo_senti_100k
from dataset import load_simplifyweibo_4_moods
from dataset import load_simplifyweibo_3_moods
from dataset import load_hotel_comment
# 来自Transformer的激活函数，效果略有提升
def gelu(x):
return 0.5 * x * (1.0 + tf.math.erf(x / tf.sqrt(2.0)))
X, y, classes = load_hotel_comment()
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8, random_state=73672)
class_weight = balance_class_weight(y_train)
num_classes = len(classes)
tokenizer = SimpleTokenizer(min_freq=32)
tokenizer.fit(X_train)
X_train = tokenizer.transform(X_train)
maxlen = 48
maxlen = find_best_maxlen(X_train)
X_train = sequence.pad_sequences(
X_train,
maxlen=maxlen,
dtype="int32",
padding="post",
truncating="post",
value=0
)
y_train = tf.keras.utils.to_categorical(y_train, num_classes)