Question

我正在尝试在我的系统中稍作修改来实现此char-rnn.py。

这是我的完整代码：

from keras.models import Sequential
from keras.layers import Dense, Activation,TimeDistributedDense, Dropout
from keras.layers import LSTM
from keras.optimizers import RMSprop
from keras.utils.data_utils import get_file
import numpy

# Obtain the corpus of character sequence to train from.
# Here it is just the sequence 123456789 repeated 100000 times.
x = "123456789"*1000

# Construct a dictionary, and the reverse dictionary for the participating chars.
# '*" is a 'start-sequence' character.
dct = ['*'] + list(set(x))
max_features = len(dct)
rev_dct = [(j, i) for i, j in enumerate(dct)]
rev_dct = dict(rev_dct)

# Convert the characters to their dct indexes.
x = [rev_dct[ch] for ch in x]

# Divide the corpuse to substrings of length 200.
n_timestamps = 200
x = x[:len(x)- len(x) % n_timestamps]
x = numpy.array(x, dtype='int32').reshape((-1, n_timestamps))

# Generate input and ouput per substring, as an indicator matrix.
y = numpy.zeros((x.shape[0], x.shape[1], max_features), dtype='int32')
for i in numpy.arange(x.shape[0]):
    for j in numpy.arange(x.shape[1]):
        y[i, j, x[i, j]] = 1

# Shift-1 the input sequences to the right, and make them start with '*'.
x = numpy.roll(y, 1, axis=1)
x[:, 0, :] = 0
x[:, 0, 0] = 1

# Build the model.

model = Sequential()
model.add(LSTM(256, return_sequences=True, batch_input_shape=x.shape))
model.add(Dense(max_features))
model.add(Activation('softmax'))

optimizer = RMSprop(lr=0.01)
model.compile(loss='categorical_crossentropy', optimizer=optimizer)


model.fit(x, y, batch_size=100, nb_epoch=1)

# Sample 128 sentences (200 characters each) from model.

def mnrnd(probs):
    rnd = numpy.random.random()
    for i in xrange(len(probs)):
        rnd -= probs[i]
        if rnd <= 0:
            return i
    return i

sentences = numpy.zeros((45, n_timestamps, max_features))
sentences[:, 0, 0] = 1

# Start sampling char-sequences. At each iteration i the probability over
# the i-th character of each sequences is computed.
for i in numpy.arange(n_timestamps):
    probs = model.predict_proba(sentences)[:,i,:]
    # Go over each sequence and sample the i-th character.
    for j in numpy.arange(len(sentences)):
        sentences[j, i+1, mnrnd(probs[j, :])] = 1
sentences = [sentence[1:].nonzero()[1] for sentence in sentences]

# Convert to readable text.
text = []
for sentence in sentences:
    text.append(''.join([dct[word] for word in sentence]))

但是我收到了这个错误：

Traceback (most recent call last):
  File "char-rnn.py", line 70, in <module>
    sentences[j, i+1, mnrnd(probs[j, :])] = 1
IndexError: index 200 is out of bounds for axis 1 with size 200

Answer 1

看起来它试图在比数据更长的序列上运行。

查看您的代码，这是抛出错误的区域：

for i in numpy.arange(n_timestamps):
probs = model.predict_proba(sentences)[:,i,:]
# Go over each sequence and sample the i-th character.
for j in numpy.arange(len(sentences)):
    sentences[j, i+1, mnrnd(probs[j, :])] = 1

问题可能是您的数据长n_timestamps，但您正在尝试预测n_timestamps + 1个字符（当您预测i +1时）。

尝试按如下方式将循环长度减少一个：

for i in numpy.arange(n_timestamps - 1):
probs = model.predict_proba(sentences)[:,i,:]
# Go over each sequence and sample the i-th character.
for j in numpy.arange(len(sentences)):
    sentences[j, i+1, mnrnd(probs[j, :])] = 1

Answer 2

操作X的方式可能有问题，我试图运行您的代码，但遇到的错误与您提到的错误不同。

我在LSTM上添加了一个不同的示例，它可以根据示例here执行您想要的操作。

以下是代码：

angular.module('app', ['formly', 'formlyBootstrap'])

char-rnn（多层递归神经网络）实现得到IndexError

2 个答案: