基于Keras2.x LSTM 唐诗生成

原创

已于 2023-04-07 16:33:52 修改 · 273 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#深度学习 #tensorflow #python

于 2023-04-07 16:32:36 首次发布

本文详细介绍了如何利用Keras2.x框架中的LSTM模型进行唐诗生成。通过训练历史诗词数据集，建立语言模型，实现自动生成符合唐诗风格的新诗句。内容涵盖数据预处理、模型构建、训练过程以及生成结果展示。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

# coding: utf8
import numpy

from keras.models import Sequential
from keras.layers.core import Dense, Activation, Dropout
from keras.layers import LSTM
import numpy as np
import random

path = './poetry.txt'
print('opening txt')
text = open(path, "r", encoding='utf-8').read().lower()
print('corpus length:', len(text))

chars = set(text)
print('total chars:', len(chars))
char_indices = dict((c, i) for i, c in enumerate(chars))
indices_char = dict((i, c) for i, c in enumerate(chars))

# cut the text in semi-redundant sequences of maxlen characters
maxlen = 40
step = 3
sentences = []
next_chars = []
for i in range(0, len(text) - maxlen, step):
    sentences.append(text[i: i + maxlen])
    next_chars.append(text[i + maxlen])
print('nb sequences:', len(sentences))

#########向量化###########

print('Vectorization...')
X = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
y = np.zeros((len(sentences), len(chars)), dtype=np.bool)
for i, sentence in enumerate(sentences):