代码语言：python

所属分类：人工智能

代码描述：python使用keras基于seq2seq实现人工智能中文聊天机器人代码

代码标签： python keras seq2seq 人工 智能 中文 聊天 机器人 代码

下面为部分代码预览，完整代码请点击下载或在bfwstudio webide中打开

#!/usr/local/python3/bin/python3
# -*- coding: utf-8 -*
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, LSTM, Dense
import numpy as np
import pandas as pd

# 定义模型超参数、迭代次数、语料路径
#Batch size 的大小
batch_size = 32
# 迭代次数epochs
epochs = 100
# 编码空间的维度Latent dimensionality
latent_dim = 256
# 要训练的样本数
num_samples = 9
#设置语料的路径
data_path = '/data/wwwroot/default/dataset/ask/askbot.txt'

# 把语料向量化
input_texts = []
target_texts = []
input_characters = set()
target_characters = set()

with open(data_path, 'r', encoding='utf-8') as f:
    lines = f.read().split('\n')
for line in lines[: min(num_samples, len(lines))]:
    # print(line)
    input_text, target_text = line.split('|')
    target_text = target_text[0:100]
    target_text = '\t' + target_text + '\n'
    input_texts.append(input_text)
    target_texts.append(target_text)

    for char in input_text:
        if char not in input_characters:
            input_characters.add(char)
    for char in target_text:
        if char not in target_characters:
            target_characters.add(char)

input_characters = sorted(list(input_characters))
target_characters = sorted(list(target_characters))
num_encoder_tokens = len(input_characters)
num_decoder_tokens = len(target_characters)
max_encoder_seq_length = max([len(txt) for txt in input_texts])
max_decoder_seq_length = max([len(txt) for txt in target_texts])

print('Number of samples:', len(input_texts))
print('Number of unique input tokens:', num_encoder_tokens)
print('Number of unique output tokens:', num_decoder_tokens)
print('Max sequence length for inputs:', max_encoder_seq_length)
print('Max sequence length for outputs:', max_decoder_seq_length)

input_token_index = dict(
    [(char, i) for i, char in enumerate(input_characters)])
target_token_index = dict(
    [(char, i) for i, char in enumerate(target_characters)])

encoder_input_data = np.zeros(
    (len(input_texts), max_encoder_seq_length, num_encoder_tokens), dtype='float32')
decoder_input_data = np.zeros(
    (len(input_texts), max_decoder_seq_length, num_decoder_tokens), dtype='float32')
decoder_target_data = np.zeros(
    (len(input_texts), max_decoder_seq_length, num_decoder_tokens), dtype='float32')

for i, (input_text, target_text) in enumerate(zip(input_texts, target_texts)):
    for t, char in enumerate(input_text):
        encoder_input_data[i, t, input_token_index[char]] = 1.
    for t, char in enumerate(target_text):
        # decoder_target_data is ahead of decoder_input_data by one timestep
        decoder_input_data[i, t, target_token_index[char]] = 1.
        if t > 0:
            # decoder_target_data will be ahead by one timestep
            # and will not include the start character.
            decoder_target_data[i, t - 1, target_token_index[char]] = 1.

# LSTM_Seq2Seq 模型定义、训练和保存
encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
# 输出 `encoder_outputs`
encoder_states = [state_h, state_c]
# 状态 `encoder_states`
decoder_inputs = Input(shape=(None, num_decoder_tokens))
decoder_lstm = LSTM(lat.........完整代码请登录后点击上方下载按钮下载查看

网友评论0

取消

评论提交中...

提交评论