def __init__(self):
self.size = 8 # LSTM神经元size
self.GO_ID = 1 # 输出序列起始标记
self.EOS_ID = 2 # 结尾标记
self.PAD_ID = 0 # 空值填充0
self.min_freq = 1 # 样本词频超过这个值才会存入词表
self.epochs = 20000 # 训练次数
self.batch_num = 1000 # 参与训练的问答对个数
self.input_seq_len = 25 # 输入序列长度
self.output_seq_len = 50 # 输出序列长度
self.init_learning_rate = 0.5 # 初始学习率
self.wordToken = word_token.WordToken()
# 放在全局的位置，为了动态算出 num_encoder_symbols 和 num_decoder_symbols
self.max_token_id = self.wordToken.load_file_list(
['./dialog/question', './dialog/answer'], self.min_freq)
self.num_encoder_symbols = self.max_token_id + 5
self.num_decoder_symbols = self.max_token_id + 5
self.sess = tf.Session()
encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate = self.get_model(
feed_previous=True)
saver.restore(self.sess, './model/' + str(self.epochs) + '/demo_')
self.encoder_inputs = encoder_inputs
self.decoder_inputs = decoder_inputs
self.target_weights = target_weights
self.outputs = outputs
PAD_ID = 0
# 输出序列起始标记
GO_ID = 1
# 结尾标记
EOS_ID = 2
# LSTM神经元size
size = 8
# 初始学习率
init_learning_rate = 1
# 在样本中出现频率超过这个值才会进入词表
min_freq = 10
# 训练的轮数
train_round = 10000
wordToken = word_token.WordToken()
# 放在全局的位置，为了动态算出num_encoder_symbols和num_decoder_symbols
max_token_id = wordToken.load_file_list(
['samples/question.txt', 'samples/answer.txt'], min_freq)
num_encoder_symbols = max_token_id + 5 #表示encoder_inputs中的整数词id的数目
num_decoder_symbols = max_token_id + 5
def get_id_list_from(sentence):
"""
获取输入句子的分词对应id列表
"""
sentence_id_list = []
seg_list = jieba.cut(sentence)
for str in seg_list:
from tensorflow.contrib.legacy_seq2seq.python.ops import seq2seq
import word_token
import jieba
import random
import bm25_fitness_data
size = 8 # LSTM神经元size
GO_ID = 1 # 输出序列起始标记
EOS_ID = 2 # 结尾标记
PAD_ID = 0 # 空值填充0
min_freq = 1 # 样本频率超过这个值才会存入词表
epochs = 20000 # 训练次数
batch_num = 1000 # 参与训练的问答对个数
input_seq_len = 25 # 输入序列长度
output_seq_len = 50 # 输出序列长度
init_learning_rate = 0.5 # 初始学习率
wordToken = word_token.WordToken() # 这是个词袋模型
max_token_id = wordToken.load_file_list(['./samples/question', './samples/answer'], min_freq)
num_encoder_symbols = max_token_id + 5 # 算上加上填充、结尾标记、输出标记
num_decoder_symbols = max_token_id + 5
APP_ID = '21290378'
API_KEY = 'ZoKi9QNvTdPseK1jOSVWvGZK'
SECRET_KEY = 'jjHqdb1SDwQBecELrc7SaWIHXnYpg8HB'
client = AipNlp(APP_ID, API_KEY, SECRET_KEY) # 调用百度词,句相似度API
options = {}
options["model"] = "bert"
q_list = [] # question
a_list = [] # answer
type_list = [] # ill type
with open('question.txt', encoding="utf-8") as f:
