RNN是一种非常强大的神经网络模型,它的输入输出都是一个向量序列。RNN就是为了序列数据建模而产生的,广泛的应用在视频、图像以及文本序列中。这里我们将介绍一个简单的RNN应用实例–RNN生成古诗词。
数据集:poetry.txt
1.训练文件 train.py
# -*- coding: utf-8 -*-
import collections
import tensorflow as tf
import numpy as np
poetry_file ="poetry.txt"
#诗集
poetrys = []
with open(poetry_file,"r",encoding = "utf-8") as f:
for line in f:
try:
title,content=line.strip().split(":")
content = content.replace(' ','')
if '_' in content or '(' in content or '(' in content or '《' in content or '[' in content:
continue
if len(content) <5 or len(content) >79:
continue
content = '[' + content + ']'
poetrys.append(content)
except Exception as e:
pass
# 按诗的字数排序
poetrys = sorted(poetrys,key=lambda line: len(line))
print('唐诗总数:',len(poetrys))
# 统计每个字出现次数
all_words = []
for poetry in poetrys:
all_words += [word for word in poetry]
counter = collections.Counter(all_words)
count_pairs = sorted(counter.items(), key=lambda x: -x[1])
words, _ = zip(*count_pairs)
# 取前多少个常用字
words = words[:len(words)] + (' ',)
# 每个字映射为一个数字ID
word_num_map = dict(zip(words, range(len(words))))
to_num = lambda word: word_num_map.get(word, len(words))
poetrys_vector = [ list(map(to_num, poetry)) for poetry in poetrys]
# 每次取64首诗进行训练
batch_size = 64
n_chunk = len(poetrys_vector) // batch_size #541
x_batches = []
y_batches = []
for i in range(n_chunk):
start_index = i * batch_size#起始位置
end_index = start_index + batch_size#结束位置
batches = poetrys_vector[start_index:end_index]
length = max(map(len,batches))#每个batches中句子的最大长度
xdata = np.full((batch_size,length), word_num_map[' '], np.int32)
for row in range(batch_size):
xdata[row,:len(batches[row])] = batches[row]
ydata = np.copy(xdata)
ydata[:,:-1] = xdata[:,1:]
"""
xdata ydata
[6,2,4,6,9] [2,4,6,9,9]
[1,4,2,8,5] [4,2,8,5,5]
"""
x_batches.append(xdata)
y_batches.append(ydata)
#---------------------------------------RNN--------------------------------------#
input_data = tf.placeholder(tf.int32, [batch_size, None])
output_targets = tf.placeholder(tf.int32, [batch_size, None])
# 定义RNN
def neural_network(model='lstm', rnn_size=128, num_layers=2):
if model == 'rnn':
cell_fun = tf.nn.rnn_cell.BasicRNNCell
elif model == 'gru':
cell_fun = tf.nn.rnn_cell.GRUCell
elif model == 'lstm':
cell_fun = tf.nn.rnn_cell.BasicLSTMCell
cell = cell_fun(rnn_size, state_is_tuple=True)
cell = tf.nn.rnn_cell.MultiRNNCell([cell] * num_layers, state_is_tuple=True)
initial_state = cell.zero_state(batch_size, tf.float32)
with tf.variable_scope('rnnlm'):
softmax_w = tf.get_variable("softmax_w", [rnn_size, len(words)+1])
softmax_b =