使用RNN / LSTM连续生成文本

Question

我发现了很多使用LSTM生成文本的例子，这是它们的基础：

# Load Larger LSTM network and generate text
import sys
import numpy
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import LSTM
from keras.callbacks import ModelCheckpoint
from keras.utils import np_utils
# load ascii text and covert to lowercase
filename = "wonderland.txt"
raw_text = open(filename).read()
raw_text = raw_text.lower()
# create mapping of unique chars to integers, and a reverse mapping
chars = sorted(list(set(raw_text)))
char_to_int = dict((c, i) for i, c in enumerate(chars))
int_to_char = dict((i, c) for i, c in enumerate(chars))
# summarize the loaded data
n_chars = len(raw_text)
n_vocab = len(chars)
print "Total Characters: ", n_chars
print "Total Vocab: ", n_vocab
# prepare the dataset of input to output pairs encoded as integers
seq_length = 100
dataX = []
dataY = []
for i in range(0, n_chars - seq_length, 1):
    seq_in = raw_text[i:i + seq_length]
    seq_out = raw_text[i + seq_length]
    dataX.append([char_to_int[char] for char in seq_in])
    dataY.append(char_to_int[seq_out])
n_patterns = len(dataX)
print "Total Patterns: ", n_patterns
# reshape X to be [samples, time steps, features]
X = numpy.reshape(dataX, (n_patterns, seq_length, 1))
# normalize
X = X / float(n_vocab)
# one hot encode the output variable
y = np_utils.to_categorical(dataY)
# define the LSTM model
model = Sequential()
model.add(LSTM(256, input_shape=(X.shape[1], X.shape[2]), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(256))
model.add(Dropout(0.2))
model.add(Dense(y.shape[1], activation='softmax'))
# load the network weights
filename = "weights-improvement-47-1.2219-bigger.hdf5"
model.load_weights(filename)
model.compile(loss='categorical_crossentropy', optimizer='adam')
# pick a random seed
start = numpy.random.randint(0, len(dataX)-1)
pattern = dataX[start]
print "Seed:"
print "\"", ''.join([int_to_char[value] for value in pattern]), "\""
# generate characters
for i in range(1000):
    x = numpy.reshape(pattern, (1, len(pattern), 1))
    x = x / float(n_vocab)
    prediction = model.predict(x, verbose=0)
    index = numpy.argmax(prediction)
    result = int_to_char[index]
    seq_in = [int_to_char[value] for value in pattern]
    sys.stdout.write(result)
    pattern.append(index)
    pattern = pattern[1:len(pattern)]
print "\nDone."

训练后，网络应该按照以下方式工作：随机播种后，它会生成一些文本。但它进入无限循环，所以生成的文本片一次又一次地重复。我知道它应该以这种方式工作，因为我们将生成的文本的最后部分提供给网络，因此它根据以前的数据预测序列。

但我想让网络连续生成不同的文本。怎么做？也许我需要多次制作随机种子，或者最好使用另外一种不同训练的网络，以便2网络能够将种子输出作为种子？

Answer 1

使用不同的sampling strategy。

现在你正在使用贪婪的搜索，你总是选择最可能的角色作为下一个。

您可以根据网络生成的概率使用随机抽样来选择新角色。为了更好地控制采样过程，通常会引入temperature parameter。这使您可以控制生成的文本的多样性。