如何在keras中使用model.predict？

Question

在为句子分类任务训练我的模型后，我正在使用 keras model.predict。我的代码是

import numpy as np
model = Sequential()
l = ['Hello this is police department', 'hello this is 911 emergency']
tokenizer = Tokenizer()
tokenizer.fit_on_texts(l)
X = tokenizer.texts_to_sequences(l)
X = np.array(X)
a = model.predict(X)
print(a)

但是输出好像是一个数组，

[[1. 2. 3. 4. 5.]
 [1. 2. 3. 6. 7.]]

我正在处理一个带有 2 个标签的句子分类任务。所以我想将这些句子预测为0 或1。而是得到一个 numpy 数组。如何进行编码以预测这两个标签之一？

Answer 1

为您的模型添加一些层。要获得 [0,1] 中的概率，请使用 sigmoid 作为最后一次激活

from sklearn.preprocessing import LabelEncoder

maxlen = 10

X_train = ['Hello this is police department', 
     'hello this is 911 emergency',
     'asdsa sadasd',
     'asnxas asxkx',
     'kas',
     'jwxxxx']
y_train = ['positive','negative','positive','negative','positive','negative']

label_enc = LabelEncoder()
label_enc.fit(y_train)

tokenizer = tf.keras.preprocessing.text.Tokenizer()
tokenizer.fit_on_texts(X_train)

X_train = tokenizer.texts_to_sequences(X_train)
X_train = tf.keras.preprocessing.sequence.pad_sequences(X_train, maxlen=maxlen)

y_train = label_enc.transform(y_train)

model = Sequential()
model.add(Dense(1, activation='sigmoid', input_shape=(maxlen,)))
model.compile('adam', 'binary_crossentropy')
model.fit(X_train,y_train, epochs=3)


### PREDICT NEW UNSEEN DATA ###

X_test = ['hello hSDAS', '911 oaoad']

X_test = tokenizer.texts_to_sequences(X_test)
X_test = tf.keras.preprocessing.sequence.pad_sequences(X_test, maxlen=maxlen)

a = (model.predict(X_test)>0.5).astype(int).ravel()
print(a)

reverse_pred = label_enc.inverse_transform(a.ravel())
print(reverse_pred)