Pybrain

Question

我在整个互联网上搜索了这个，没有找到任何东西，除了堆栈溢出 'deleted' post。

问题如下： PyBrain LSTM + SequencialDataSet 上的每个示例和教程都会给我以下错误：

TypeError: slice indices must be integers or None or have an __index__ method

根据我之前的搜索，这似乎是一个问题，在某个版本的 python 之后，整数运算 returns float 而不是整数

但是，它似乎适用于像我一样使用 python 2.x 的其他人。有什么想法吗？

代码（不是我的，取自另一个 Whosebug post）：

from pybrain.tools.shortcuts import buildNetwork
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.datasets import SequentialDataSet
from pybrain.structure import SigmoidLayer, LinearLayer
from pybrain.structure import LSTMLayer

import itertools
import numpy as np

INPUTS = 5
OUTPUTS = 1
HIDDEN = 40

net = buildNetwork(INPUTS, HIDDEN, OUTPUTS, hiddenclass=LSTMLayer,     outclass=LinearLayer, recurrent=True, bias=True)

ds = SequentialDataSet(INPUTS, OUTPUTS)
ds.addSample([0,1,2,3,4],[5])
ds.addSample([5,6,7,8,9],[10])
ds.addSample([10,11,12,13,14],[15])
ds.addSample([16,17,18,19,20],[21])

net.randomize()

trainer = BackpropTrainer(net, ds)

for _ in range(1000):
    print trainer.train()

x=net.activate([0,1,2,3,4])
print x

这给了我这个错误：

File "try3.py", line 27, in <module>
print trainer.train()
File "/usr/local/lib/python2.7/dist-packages/PyBrain-0.3.3-py2.7.egg/pybrain/supervised/trainers/backprop.py", line 57, in train
for seq in self.ds._provideSequences():
File "/usr/local/lib/python2.7/dist-packages/PyBrain-0.3.3-py2.7.egg/pybrain/datasets/sequential.py", line 173, in _provideSequences
return iter(map(list, iter(self)))
File "/usr/local/lib/python2.7/dist-packages/PyBrain-0.3.3-py2.7.egg/pybrain/datasets/sequential.py", line 169, in __iter__
yield self.getSequenceIterator(i)
File "/usr/local/lib/python2.7/dist-packages/PyBrain-0.3.3-py2.7.egg/pybrain/datasets/sequential.py", line 63, in getSequenceIterator
return zip(*self.getSequence(index))
File "/usr/local/lib/python2.7/dist-packages/PyBrain-0.3.3-py2.7.egg/pybrain/datasets/sequential.py", line 56, in getSequence
return [self._getSequenceField(index, l) for l in self.link]
File "/usr/local/lib/python2.7/dist-packages/PyBrain-0.3.3-py2.7.egg/pybrain/datasets/sequential.py", line 45, in _getSequenceField
return self.getField(field)[seq[index]:]
TypeError: slice indices must be integers or None or have an __index__ method

使用：

Python 2.7.6 (default, Oct 26 2016, 20:30:19)
[GCC 4.8.4] on linux2

Answer 1

找到了，不同之处在于 pybrain，这在我的设置中修复了它：

pip uninstall pybrain
pip install pybrain

试试看，

Pybrain - 使用 Backprop 训练器的 SequentialDataSet 给出切片索引错误

Pybrain - SequentialDataSet using Backprop trainer give a slice indices error

python

neural-network

lstm