Tensorflow预测两个句子相互追逐的可能性

import tensorflow as tf
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

# 定义训练数据
sentences = ['句子1', '句子2', ...]  # 包含两个句子的训练数据
labels = [0, 1, ...]  # 对应句子是否相互追逐的标签，0表示不追逐，1表示追逐

# 创建分词器
tokenizer = Tokenizer()
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index

# 将句子转换为序列
sequences = tokenizer.texts_to_sequences(sentences)

# 对序列进行填充，使其长度相同
max_length = max(len(seq) for seq in sequences)
padded_sequences = pad_sequences(sequences, maxlen=max_length)

# 构建模型
model = tf.keras.Sequential([
    tf.keras.layers.Embedding(len(word_index) + 1, 100, input_length=max_length),
    tf.keras.layers.Bidirectional(tf.keras.layers.GRU(64)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

# 编译模型
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# 训练模型
model.fit(padded_sequences, labels, epochs=10)

# 使用模型进行预测
test_sentence = ['句子1', '句子2']  # 需要预测的句子
test_sequence = tokenizer.texts_to_sequences(test_sentence)
test_padded_sequence = pad_sequences(test_sequence, maxlen=max_length)
predictions = model.predict(test_padded_sequence)

# 打印预测结果
for i, sentence in enumerate(test_sentence):
    print(f"句子'{sentence}'的预测结果为：{predictions[i]}")