TensorFlow练习7: 基于RNN生成古诗词
RNN不像传统的神经网络-它们的输出输出是固定的,而RNN允许我们输入输出向量序列。RNN是为了对序列数据进行建模而产生的。
样本序列性:样本间存在顺序关系,每个样本和它之前的样本存在关联。比如说,在文本中,一个词和它前面的词是有关联的;在气象数据中,一天的气温和前几天的气温是有关联的。
例如本帖要使用RNN生成古诗,你给它输入一堆古诗词,它会学着生成和前面相关联的字词。如果你给它输入一堆姓名,它会学着生成姓名;给它输入一堆古典乐/歌词,它会学着生成古典乐/歌词,甚至可以给它输入源代码。
关于RNN:
- TensorFlow练习3: RNN, Recurrent Neural Networks
- http://karpathy.github.io/2015/05/21/rnn-effectiveness/
本帖代码移植自char-rnn,它是基于Torch的洋文模型,稍加修改即可应用于中文。char-rnn使用文本文件做为输入、训练RNN模型,然后使用它生成和训练数据类似的文本。
使用的数据集:全唐诗(43030首):https://pan.baidu.com/s/1o7QlUhO
训练:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
import collections
import numpy as np
import tensorflow as tf
#-------------------------------数据预处理---------------------------#
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))))
# 把诗转换为向量形式,参考TensorFlow练习1
to_num = lambda word: word_num_map.get(word, len(words))
poetrys_vector = [ list(map(to_num, poetry)) for poetry in poetrys]
#[[314, 3199, 367, 1556, 26, 179, 680, 0, 3199, 41, 506, 40, 151, 4, 98, 1],
#[339, 3, 133, 31, 302, 653, 512, 0, 37, 148, 294, 25, 54, 833, 3, 1, 965, 1315, 377, 1700, 562, 21, 37, 0, 2, 1253, 21, 36, 264, 877, 809, 1]
#....]
# 每次取64首诗进行训练
batch_size = 64
n_chunk = len(poetrys_vector) // batch_size
x_batches = []
y_batches = []
for i in range(n_chunk):
start_index = i * batch_size
end_index = start_index + batch_size
batches = poetrys_vector[start_index:end_index]
length = max(map(len,batches))
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 = tf.get_variable("softmax_b", [len(words)+1])
with tf.device("/cpu:0"):
embedding = tf.get_variable("embedding", [len(words)+1, rnn_size])
inputs = tf.nn.embedding_lookup(embedding, input_data)
outputs, last_state = tf.nn.dynamic_rnn(cell, inputs, initial_state=initial_state, scope='rnnlm')
output = tf.reshape(outputs,[-1, rnn_size])
logits = tf.matmul(output, softmax_w) + softmax_b
probs = tf.nn.softmax(logits)
return logits, last_state, probs, cell, initial_state
#训练
def train_neural_network():
logits, last_state, _, _, _ = neural_network()
targets = tf.reshape(output_targets, [-1])
loss = tf.nn.seq2seq.sequence_loss_by_example([logits], [targets], [tf.ones_like(targets, dtype=tf.float32)], len(words))
cost = tf.reduce_mean(loss)
learning_rate = tf.Variable(0.0, trainable=False)
tvars = tf.trainable_variables()
grads, _ = tf.clip_by_global_norm(tf.gradients(cost, tvars), 5)
optimizer = tf.train.AdamOptimizer(learning_rate)
train_op = optimizer.apply_gradients(zip(grads, tvars))
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver(tf.all_variables())
for epoch in range(50):
sess.run(tf.assign(learning_rate, 0.002 * (0.97 ** epoch)))
n = 0
for batche in range(n_chunk):
train_loss, _ , _ = sess.run([cost, last_state, train_op], feed_dict={input_data: x_batches[n], output_targets: y_batches[n]})
n += 1
print(epoch, batche, train_loss)
if epoch % 7 == 0:
saver.save(sess, 'poetry.module', global_step=epoch)
train_neural_network()
|
使用训练好的模型生成古诗:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
|
import collections
import numpy as np
import tensorflow as tf
#-------------------------------数据预处理---------------------------#
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))))
# 把诗转换为向量形式,参考TensorFlow练习1
to_num = lambda word: word_num_map.get(word, len(words))
poetrys_vector = [ list(map(to_num, poetry)) for poetry in poetrys]
#[[314, 3199, 367, 1556, 26, 179, 680, 0, 3199, 41, 506, 40, 151, 4, 98, 1],
#[339, 3, 133, 31, 302, 653, 512, 0, 37, 148, 294, 25, 54, 833, 3, 1, 965, 1315, 377, 1700, 562, 21, 37, 0, 2, 1253, 21, 36, 264, 877, 809, 1]
#....]
batch_size = 1
n_chunk = len(poetrys_vector) // batch_size
x_batches = []
y_batches = []
for i in range(n_chunk):
start_index = i * batch_size
end_index = start_index + batch_size
batches = poetrys_vector[start_index:end_index]
length = max(map(len,batches))
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 = tf.get_variable("softmax_b", [len(words)+1])
with tf.device("/cpu:0"):
embedding = tf.get_variable("embedding", [len(words)+1, rnn_size])
inputs = tf.nn.embedding_lookup(embedding, input_data)
outputs, last_state = tf.nn.dynamic_rnn(cell, inputs, initial_state=initial_state, scope='rnnlm')
output = tf.reshape(outputs,[-1, rnn_size])
logits = tf.matmul(output, softmax_w) + softmax_b
probs = tf.nn.softmax(logits)
return logits, last_state, probs, cell, initial_state
#-------------------------------生成古诗---------------------------------#
# 使用训练完成的模型
def gen_poetry():
def to_word(weights):
t = np.cumsum(weights)
s = np.sum(weights)
sample = int(np.searchsorted(t, np.random.rand(1)*s))
return words[sample]
_, last_state, probs, cell, initial_state = neural_network()
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver(tf.all_variables())
saver.restore(sess, 'poetry.module-49')
state_ = sess.run(cell.zero_state(1, tf.float32))
x = np.array([list(map(word_num_map.get, '['))])
[probs_, state_] = sess.run([probs, last_state], feed_dict={input_data: x, initial_state: state_})
word = to_word(probs_)
#word = words[np.argmax(probs_)]
poem = ''
while word != ']':
poem += word
x = np.zeros((1,1))
x[0,0] = word_num_map[word]
[probs_, state_] = sess.run([probs, last_state], feed_dict={input_data: x, initial_state: state_})
word = to_word(probs_)
#word = words[np.argmax(probs_)]
return poem
print(gen_poetry())
|
生成的“诗词”(至少格式对上了):
1
2
3
4
5
6
7
8
9
10
11
12
13
|
新犬随风起,一璃迹阵悲。
浅昏罢庄哉,清插去园空。
双叶坐成鉴,王妓水正苑。
鸟声不成影,胙滩朱瓮声。
无斑红芜踏,那期日正闲。
吾燕登无士,无处得赵名。
并灭图微蒿,淮头水十荔。
晴花尚乘望,官宽留可求。
最忆青州守,英仍临阳峰。
生人隔天道,在国思山田。
登临闭石土,阵下一欢娱。
林暝今又少,孙频唯在愁。
|
生成藏头诗:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
|
def gen_poetry_with_head(head):
def to_word(weights):
t = np.cumsum(weights)
s = np.sum(weights)
sample = int(np.searchsorted(t, np.random.rand(1)*s))
return words[sample]
_, last_state, probs, cell, initial_state = neural_network()
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver(tf.all_variables())
saver.restore(sess, 'poetry.module-49')
state_ = sess.run(cell.zero_state(1, tf.float32))
poem = ''
i = 0
for word in head:
while word != ',' and word != '。':
poem += word
x = np.array([list(map(word_num_map.get, word))])
[probs_, state_] = sess.run([probs, last_state], feed_dict={input_data: x, initial_state: state_})
word = to_word(probs_)
time.sleep(1)
if i % 2 == 0:
poem += ','
else:
poem += '。'
i += 1
return poem
print(gen_poetry_with_head('一二三四'))
|
上面使用的TensroFlow版本为0.11,0.12版本貌似不能直接运行,简单修改如下代码:
读取模型的方法:
1
2
3
|
module_file = tf.train.latest_checkpoint('.')
#print(module_file)
saver.restore(sess, module_file)
|
tf.initialize_all_variables() deprecated,使用tf.global_variables_initializer()替代。
- https://github.com/ryankiros/neural-storyteller(根据图片生成故事)
TensorFlow练习7: 基于RNN生成古诗词相关推荐
- java rnn生成古诗_Tensorflow 基于RNN生成古诗词 自己的实践
在网上看到一篇利用Tensorflow+RNN模型生成古诗词的练习,觉得挺有意思的便自己来试了下,算是熟悉下Tensorflow+NLP的基本操作流程 首先pip 安装NLTK 在你的Tensorfl ...
- python输出古诗词_TensorFlow:基于RNN生成古诗词
时间:2017-07-26 发布人:SHX 浏览次数:3806 评论:0 实例来源于网络,但是以前的代码都是基于TensorFlow1.0以前的版本写的,实际运行时会报错,对于小白来说是一头雾水.这里 ...
- TensorFlow2学习:RNN生成古诗词
本文转自 AI科技大本营 TensorFlow2学习:RNN生成古诗词 文章不见了可以参考这位博主的文章 公众号的文章写得挺好的,这里简单介绍下思路及值得学习的地方 模型简介 模型不算多么复杂高大上, ...
- 基于RNN实现古诗词生成模型
我们知道,RNN(循环神经网络)模型是基于当前的状态和当前的输入来对下一时刻做出预判.而LSTM(长短时记忆网络)模型则可以记忆距离当前位置较远的上下文信息. 在此,我们根据上述预判模型来进行 古诗词 ...
- TensorFlow教程使用RNN生成唐诗
本教程转载至:TensorFlow练习7: 基于RNN生成古诗词 使用的数据集是全唐诗,首先提供一下数据集的下载链接:https://pan.baidu.com/s/13pNWfffr5HSN79WN ...
- Tensorflow:基于LSTM生成藏头诗
Tensorflow:基于LSTM生成藏头诗 最近在学习TensorFlow,学习到了RNN这一块,相关的资料不是很多,了解到使用RNN可以生成藏头诗之后,我就决定拿这个下手啦! 本文不介绍RNN以及 ...
- 基于RNN的中文古诗词生成神经网络实现
一.前言 1.图解RNN 2.Tensorflow中RNN实现的正确打开方式 二.实战 1.训练数据处理 (1)文字转为向量 def _get_poetry(self):with open(self. ...
- java rnn生成古诗_Tensorflow:基于LSTM轻松生成各种古诗
原标题:Tensorflow:基于LSTM轻松生成各种古诗 本文代码在公众号 datadw 里 回复古诗即可获取. RNN不像传统的神经网络-它们的输出输出是固定的,而RNN允许我们输入输出向量序列. ...
- tensorflow循环神经网络(RNN)文本生成莎士比亚剧集
tensorflow循环神经网络(RNN)文本生成莎士比亚剧集 我们将使用 Andrej Karpathy 在<循环神经网络不合理的有效性>一文中提供的莎士比亚作品数据集.给定此数据中的一 ...
最新文章
- win10无法连接wifi_手机连接WIFI但是无法上网?3个办法帮您解决!
- 2.3.NLTK工具包安装、分词、Text对象、停用词、过滤掉停用词、词性标注、分块、命名实体识别、数据清洗实例、参考文章
- 女生来大姨妈该怎么哄她?
- 安装mysql没有提示设置密码_18.04安装mysql没有提示输入密码
- 谷歌10月15日发布 Pixel 4;高通以31亿美元收购与TDK公司权益;甲骨文、VMware就云技术及支持达成协议……...
- 流量 起伏大_广西崇左的德天跨国大瀑布,一半是中国一半是越南,天下奇观!...
- 40岁了,突然公司黄了,怎么办?
- Swift项目中不能定义OC类继承Swift类
- java中clone方法_Java Object clone()方法– Java中的克隆
- 参数化三维管网建模系统MagicPipe3D
- 三菱 J2 J2S J3 J4 编码器 电机文件 修改ID 修改功率 修改型号
- flutter 弹幕 yzl_flutter_bulletchat的使用
- (转)MySQL数据库InnoDB存储引擎的磁盘空间利用率分析
- Python xldr 读取xls 文件中时间格式处理
- 计算机网络技术中的单位换算,计算机存储/网络传输中单位换算1000还是1024
- 爬虫 + 自动化利器 selenium 之自学成才篇(二)
- m4a怎么转换成mp3,4招搞定
- 车道线检测1-传统算法相关简介
- 本草纲目pdf彩图版下载_本草纲目下载|本草纲目彩色图集精编珍藏版下载pdf高清版下载_最火手机站...
- Mozilla研究—mozilla中的设计亮点