|
Seq2Seq 属于 Encoder-Decoder 结构。基本思想就是利用两个 RNN，一个 RNN 作为 Encoder，另一个 RNN 作为 Decoder。Encoder 负责将输入序列压缩成指定长度的向量，这个向量就可以看成是这个序列的语义，这个过程称为编码。Decoder负责告诉模型对应的输出是什么。两个RNN通过语义向量连接，得以实现输入与输出长度不同。
from keras.models import Model
from 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 = 5000
#设置语料的路径
data_path = './中文bot数据.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('\t')
# We use "tab" as the "start sequence" character
# for the targets, and "\n" as "end sequence" character.
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(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
# 定义模型
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
# 训练
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
model.summary()
model.fit([encoder_input_data, decoder_input_data], decoder_target_data,
batch_size=batch_size,
epochs=epochs,
validation_split=0.2)
# 保存模型
model.save('s2s.h5')
# Seq2Seq 的 Encoder 操作
encoder_model = Model(encoder_inputs, encoder_states)
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(
decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model(
[decoder_inputs] + decoder_states_inputs,
[decoder_outputs] + decoder_states)
# 把索引和分词转成序列
reverse_input_char_index = dict(
(i, char) for char, i in input_token_index.items())
reverse_target_char_index = dict(
(i, char) for char, i in target_token_index.items())
# 定义预测函数，先使用预模型预测，然后编码成汉字结果
def decode_sequence(input_seq):
# Encode the input as state vectors.
states_value = encoder_model.predict(input_seq)
#print(states_value)
# Generate empty target sequence of length 1.
target_seq = np.zeros((1, 1, num_decoder_tokens))
# Populate the first character of target sequence with the start character.
target_seq[0, 0, target_token_index['\t']] = 1.
# Sampling loop for a batch of sequences
# (to simplify, here we assume a batch of size 1).
stop_condition = False
decoded_sentence = ''
while not stop_condition:
output_tokens, h, c = decoder_model.predict(
[target_seq] + states_value)
# Sample a token
sampled_token_index = np.argmax(output_tokens[0, -1, :])
sampled_char = reverse_target_char_index[sampled_token_index]
decoded_sentence += sampled_char
if (sampled_char == '\n' or
len(decoded_sentence) > max_decoder_seq_length):
stop_condition = True
# Update the target sequence (of length 1).
target_seq = np.zeros((1, 1, num_decoder_tokens))
target_seq[0, 0, sampled_token_index] = 1.
# 更新状态
states_value = [h, c]
return decoded_sentence
# 模型预测
def predict_ans(question):
inseq = np.zeros((1, max_encoder_seq_length, num_encoder_tokens), dtype='float16')
for t, char in enumerate(question):
inseq[0, t, input_token_index[char]] = 1.
decoded_sentence = decode_sequence(inseq)
return decoded_sentence
print('Decoded sentence:', predict_ans("你是ai?"))
原文： https://soyoger.blog.csdn.net/article/details/108729400
|