欢迎来到TensorFlow入门实操课程的学习 MOOC TensorFlow入门实操课程代码回顾总结（一） MOOC TensorFlow入门实操课程代码回顾总结（二）
注：
代码语言：javascript复制用于表示python代码粘贴运行结果
目录
- 10 文本生成——循环神经网络设计
-
- 10.1 导入库
- 10.2 将歌词中的数据进行词条化
- 10.3 创建神经网络的输入序列
- 10.4 建立神经网路训练数据
- 10.5 绘制准确率曲线
- 10.6 模型评估
- 10（综） 项目实战——生成优美的诗歌
10 文本生成——循环神经网络设计
10.1 导入库
代码语言：javascript复制import tensorflow as tf
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import Embedding, LSTM, Dense, Bidirectional
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
import numpy as np
import time10.2 将歌词中的数据进行词条化
代码语言：javascript复制#print(time.time())
tokenizer = Tokenizer()
data="In the town of Athy one Jeremy Lanigan n Battered away til he hadnt a pound. nHis father died and made him a man again n Left him a farm and ten acres of ground. nHe gave a grand party for friends and relations nWho didnt forget him when come to the wall, nAnd if youll but listen Ill make your eyes glisten nOf the rows and the ructions of Lanigans Ball. nMyself to be sure got free invitation, nFor all the nice girls and boys I might ask, nAnd just in a minute both friends and relations nWere dancing round merry as bees round a cask. nJudy ODaly, that nice little milliner, nShe tipped me a wink for to give her a call, nAnd I soon arrived with Peggy McGilligan nJust in time for Lanigans Ball. nThere were lashings of punch and wine for the ladies, nPotatoes and cakes; there was bacon and tea, nThere were the Nolans, Dolans, OGradys nCourting the girls and dancing away. nSongs they went round as plenty as water, nThe harp that once sounded in Taras old hall,nSweet Nelly Gray and The Rat Catchers Daughter,nAll singing together at Lanigans Ball. nThey were doing all kinds of nonsensical polkas nAll round the room in a whirligig. nJulia and I, we banished their nonsense nAnd tipped them the twist of a reel and a jig. nAch mavrone, how the girls got all mad at me nDanced til youd think the ceiling would fall. nFor I spent three weeks at Brooks Academy nLearning new steps for Lanigans Ball. nThree long weeks I spent up in Dublin, nThree long weeks to learn nothing at all,n Three long weeks I spent up in Dublin, nLearning new steps for Lanigans Ball. nShe stepped out and I stepped in again, nI stepped out and she stepped in again, nShe stepped out and I stepped in again, nLearning new steps for Lanigans Ball. nBoys were all merry and the girls they were hearty nAnd danced all around in couples and groups, nTil an accident happened, young Terrance McCarthy nPut his right leg through miss Finnertys hoops. nPoor creature fainted and cried Meelia murther, nCalled for her brothers and gathered them all. nCarmody swore that hed go no further nTil he had satisfaction at Lanigans Ball. nIn the midst of the row miss Kerrigan fainted, nHer cheeks at the same time as red as a rose. nSome of the lads declared she was painted, nShe took a small drop too much, I suppose. nHer sweetheart, Ned Morgan, so powerful and able, nWhen he saw his fair colleen stretched out by the wall, nTore the left leg from under the table nAnd smashed all the Chaneys at Lanigans Ball. nBoys, oh boys, twas then there were runctions. nMyself got a lick from big Phelim McHugh. nI soon replied to his introduction nAnd kicked up a terrible hullabaloo. nOld Casey, the piper, was near being strangled. nThey squeezed up his pipes, bellows, chanters and all. nThe girls, in their ribbons, they got all entangled nAnd that put an end to Lanigans Ball."
corpus = data.lower().split("n")
tokenizer.fit_on_texts(corpus)
total_words = len(tokenizer.word_index) 1
print(tokenizer.word_index)
print(total_words)
10.3 创建神经网络的输入序列
代码语言：javascript复制input_sequences = []
for line in corpus:
token_list = tokenizer.texts_to_sequences([line])[0]
for i in range(1, len(token_list)):
n_gram_sequence = token_list[:i 1]
input_sequences.append(n_gram_sequence)
# pad sequences
max_sequence_len = max([len(x) for x in input_sequences])
input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))
# create predictors and label
xs, labels = input_sequences[:,:-1],input_sequences[:,-1]
ys = tf.keras.utils.to_categorical(labels, num_classes=total_words)## 查看歌词第一句话的对应编码
print(tokenizer.word_index['in'])
print(tokenizer.word_index['the'])
print(tokenizer.word_index['town'])
print(tokenizer.word_index['of'])
print(tokenizer.word_index['athy'])
print(tokenizer.word_index['one'])
print(tokenizer.word_index['jeremy'])
print(tokenizer.word_index['lanigan'])代码语言：javascript复制4 2 66 8 67 68 69 70
# 查看创建的数据
print(xs[6])代码语言：javascript复制0 0 0 4 2 66 8 67 68 69
# 查看数据的标签
print(ys[6]) # 使用独热码对其进行编码代码语言：javascript复制0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
print(xs[5])
print(ys[5])0 0 0 0 4 2 66 8 67 68
10.4 建立神经网路训练数据
代码语言：javascript复制model = Sequential()
model.add(Embedding(total_words, 64, input_length=max_sequence_len-1))
model.add(Bidirectional(LSTM(20)))
model.add(Dense(total_words, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
history = model.fit(xs, ys, epochs=500, verbose=1)
10.5 绘制准确率曲线
代码语言：javascript复制import matplotlib.pyplot as plt
def plot_graphs(history, string):
plt.plot(history.history[string])
plt.xlabel("Epochs")
plt.ylabel(string)
plt.show()
plot_graphs(history, 'accuracy')
10.6 模型评估
代码语言：javascript复制seed_text = "Laurence went to dublin"
next_words = 100
for _ in range(next_words):
token_list = tokenizer.texts_to_sequences([seed_text])[0]
token_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre')
predicted = model.predict_classes(token_list, verbose=0)
output_word = ""
for word, index in tokenizer.word_index.items():
if index == predicted:
output_word = word
break
seed_text = " " output_word
print(seed_text)
print(time.time())
10（综） 项目实战——生成优美的诗歌
代码语言：javascript复制import tensorflow as tf
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import Embedding, LSTM, Dense, Bidirectional
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
import numpy as np
import timeprint(time.time())
# !wget --no-check-certificate
# https://storage.googleapis.com/laurencemoroney-blog.appspot.com/irish-lyrics-eof.txt
# -O irish-lyrics-eof.txt代码语言：javascript复制1612176669.77111
tokenizer = Tokenizer()
data = open('/home/zzr/data/irish-lyrics-eof.txt').read()
corpus = data.lower().split("n")
tokenizer.fit_on_texts(corpus)
total_words = len(tokenizer.word_index) 1
print(tokenizer.word_index)
print(total_words)
input_sequences = []
for line in corpus:
token_list = tokenizer.texts_to_sequences([line])[0]
for i in range(1, len(token_list)):
n_gram_sequence = token_list[:i 1]
input_sequences.append(n_gram_sequence)
# pad sequences
max_sequence_len = max([len(x) for x in input_sequences])
input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))
# create predictors and label
xs, labels = input_sequences[:,:-1],input_sequences[:,-1]
ys = tf.keras.utils.to_categorical(labels, num_classes=total_words)
print(tokenizer.word_index['in'])
print(tokenizer.word_index['the'])
print(tokenizer.word_index['town'])
print(tokenizer.word_index['of'])
print(tokenizer.word_index['athy'])
print(tokenizer.word_index['one'])
print(tokenizer.word_index['jeremy'])
print(tokenizer.word_index['lanigan'])代码语言：javascript复制8 1 71 6 713 39 1790 1791
print(xs[6])
print(ys[6])代码语言：javascript复制0 0 0 0 0 0 0 0 0 0 0 0 0 0 2
print(xs[5])
print(ys[5])代码语言：javascript复制0 0 0 0 0 0 0 0 0 51 12 96 1217 48 2
print(tokenizer.word_index)
model = Sequential()
model.add(Embedding(total_words, 100, input_length=max_sequence_len-1))
model.add(Bidirectional(LSTM(150)))
model.add(Dense(total_words, activation='softmax'))
adam = Adam(lr=0.01)
model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])
#earlystop = EarlyStopping(monitor='val_loss', min_delta=0, patience=5, verbose=0, mode='auto')
history = model.fit(xs, ys, epochs=10, verbose=1)
#print model.summary()
print(model)
import matplotlib.pyplot as plt
def plot_graphs(history, string):
plt.plot(history.history[string])
plt.xlabel("Epochs")
plt.ylabel(string)
plt.show()
plot_graphs(history, 'accuracy')
next_words = 100
for _ in range(next_words):
token_list = tokenizer.texts_to_sequences([seed_text])[0]
token_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre')
predicted = model.predict_classes(token_list, verbose=0)
output_word = ""
for word, index in tokenizer.word_index.items():
if index == predicted:
output_word = word
break
seed_text = " " output_word
print(seed_text)
print(time.time())
