从尼采作品中产生文本的范例脚本
代码注释
'''Example script to generate text from Nietzsche's writings.
从尼采作品中产生文本的范例脚本
At least 20 epochs are required before the generated text
starts sounding coherent.
至少需要20个周期，使生成的文本开始连贯
It is recommended to run this script on GPU, as recurrent
networks are quite computationally intensive.
建议在GPU上运行此脚本，因为循环网络是计算密集型的。
If you try this script on new data, make sure your corpus
has at least ~100k characters. ~1M is better.
如果你尝试这个脚本在新的数据（集）上，确保你的语料库至少有100K字符。1M（字符）更好。
'''
from __future__ import print_function
from keras.callbacks import LambdaCallback
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.layers import LSTM
from keras.optimizers import RMSprop
from keras.utils.data_utils import get_file
import numpy as np
import random
import sys
import io
path = get_file('nietzsche.txt', origin='https://s3.amazonaws.com/text-datasets/nietzsche.txt')
with io.open(path, encoding='utf-8') as f:
text = f.read().lower()
print('corpus length:', len(text))
chars = sorted(list(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
# 文本切分
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))
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):
for t, char in enumerate(sentence):
x[i, t, char_indices[char]] = 1
y[i, char_indices[next_chars[i]]] = 1
# build the model: a single LSTM
# 建立单LSTM模型
print('Build model...')
model = Sequential()
model.add(LSTM(128, input_shape=(maxlen, len(chars))))
model.add(Dense(len(chars)))
model.add(Activation('softmax'))
optimizer = RMSprop(lr=0.01)
model.compile(loss='categorical_crossentropy', optimizer=optimizer)
def sample(preds, temperature=1.0):
# helper function to sample an index from a probability array
# 帮助从概率数组中采样索引的辅助函数
preds = np.asarray(preds).astype('float64')
preds = np.log(preds) / temperature
exp_preds = np.exp(preds)
preds = exp_preds / np.sum(exp_preds)
probas = np.random.multinomial(1, preds, 1)
return np.argmax(probas)
def on_epoch_end(epoch, logs):
# Function invoked at end of each epoch. Prints generated text.
# 在每个周期的末尾调用函数。打印生成的文本。
print()
print('----- Generating text after Epoch: %d' % epoch)
start_index = random.randint(0, len(text) - maxlen - 1)
for diversity in [0.2, 0.5, 1.0, 1.2]:
print('----- diversity:', diversity)
generated = ''
sentence = text[start_index: start_index + maxlen]
generated += sentence
print('----- Generating with seed: "' + sentence + '"')
sys.stdout.write(generated)
for i in range(400):
x_pred = np.zeros((1, maxlen, len(chars)))
for t, char in enumerate(sentence):
x_pred[0, t, char_indices[char]] = 1.
preds = model.predict(x_pred, verbose=0)[0]
next_index = sample(preds, diversity)
next_char = indices_char[next_index]
generated += next_char
sentence = sentence[1:] + next_char
sys.stdout.write(next_char)
sys.stdout.flush()
print()
print_callback = LambdaCallback(on_epoch_end=on_epoch_end)
model.fit(x, y,
batch_size=128,
epochs=60,
callbacks=[print_callback])
代码执行
Keras详细介绍
中文：http://keras-cn.readthedocs.io/en/latest/
实例下载
https://github.com/keras-team/keras
https://github.com/keras-team/keras/tree/master/examples
完整项目下载
方便没积分童鞋，请加企鹅452205574，共享文件夹。
包括：代码、数据集合（图片）、已生成model、安装库文件等。
