Question

我从文档中借用了一个想法here，使用RBMs + Logistic回归进行分类。

但是我收到一个不应该抛出的错误，因为我的数据矩阵中的所有条目都是数字。

代码：

from sklearn import preprocessing, cross_validation
from scipy.ndimage import convolve
from sklearn.neural_network import BernoulliRBM
from sklearn.pipeline import Pipeline
from sklearn import linear_model, datasets, metrics
import numpy as np

# create fake dataset
data, labels = datasets.make_classification(n_samples=250000)
data = preprocessing.scale(data)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(data, labels, test_size=0.7, random_state=0)

# print details
print X_train.shape, X_test.shape, y_train.shape, y_test.shape
print np.max(X_train) 
print np.min(X_train)
print np.mean(X_train, axis=0)
print np.std(X_train, axis=0)

if np.sum(np.isnan(X_train)) or np.sum(np.isnan(X_test)):
    print "NaN found!"

if np.sum(np.isnan(y_train)) or np.sum(np.isnan(y_test)):
    print "NaN found!"

if np.sum(np.isinf(X_train)) or np.sum(np.isinf(X_test)):
    print "Inf found!"

if np.sum(np.isinf(y_train)) or np.sum(np.isinf(y_test)):
    print "Inf found!"  

# train and test
logistic = linear_model.LogisticRegression()
rbm = BernoulliRBM(random_state=0, verbose=True)
classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])

# Training RBM-Logistic Pipeline
classifier.fit(X_train, y_train)

# Training Logistic regression
logistic_classifier = linear_model.LogisticRegression(C=100.0)
logistic_classifier.fit(X_train, y_train)

print("Logistic regression using RBM features:\n%s\n" % (
    metrics.classification_report(
        y_test,
        classifier.predict(X_test))))

输出继电器：

(73517, 3) (171540, 3) (73517,) (171540,)
2.0871168057
-2.21062647188
[-0.00237028 -0.00104526  0.00330683]
[ 0.99907225  0.99977328  1.00225843]
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/usr/lib/python2.7/dist-packages/IPython/utils/py3compat.pyc in execfile(fname, *where)
    173             else:
    174                 filename = fname
--> 175             __builtin__.execfile(filename, *where)

/home/test.py in <module>()
     75 
     76 # Training RBM-Logistic Pipeline

---> 77 classifier.fit(X_train, y_train)
     78 
     79 # Training Logistic regression


/usr/local/lib/python2.7/dist-packages/sklearn/pipeline.pyc in fit(self, X, y, **fit_params)
    128         data, then fit the transformed data using the final estimator.
    129         """
--> 130         Xt, fit_params = self._pre_transform(X, y, **fit_params)
    131         self.steps[-1][-1].fit(Xt, y, **fit_params)
    132         return self

/usr/local/lib/python2.7/dist-packages/sklearn/pipeline.pyc in _pre_transform(self, X, y, **fit_params)
    118         for name, transform in self.steps[:-1]:
    119             if hasattr(transform, "fit_transform"):
--> 120                 Xt = transform.fit_transform(Xt, y, **fit_params_steps[name])
    121             else:
    122                 Xt = transform.fit(Xt, y, **fit_params_steps[name]) \

/usr/local/lib/python2.7/dist-packages/sklearn/base.pyc in fit_transform(self, X, y, **fit_params)
    409         else:
    410             # fit method of arity 2 (supervised transformation)

--> 411             return self.fit(X, y, **fit_params).transform(X)
    412 
    413 

/usr/local/lib/python2.7/dist-packages/sklearn/neural_network/rbm.pyc in fit(self, X, y)
    304 
    305             for batch_slice in batch_slices:
--> 306                 pl_batch = self._fit(X[batch_slice], rng)
    307 
    308                 if verbose:

/usr/local/lib/python2.7/dist-packages/sklearn/neural_network/rbm.pyc in _fit(self, v_pos, rng)
    245 
    246         if self.verbose:
--> 247             return self.score_samples(v_pos)
    248 
    249     def score_samples(self, v):

/usr/local/lib/python2.7/dist-packages/sklearn/neural_network/rbm.pyc in score_samples(self, v)
    268         fe_ = self._free_energy(v_)
    269 
--> 270         return v.shape[1] * logistic_sigmoid(fe_ - fe, log=True)
    271 
    272     def fit(self, X, y=None):

/usr/local/lib/python2.7/dist-packages/sklearn/utils/extmath.pyc in logistic_sigmoid(X, log, out)
    498     """
    499     is_1d = X.ndim == 1
--> 500     X = array2d(X, dtype=np.float)
    501 
    502     n_samples, n_features = X.shape

/usr/local/lib/python2.7/dist-packages/sklearn/utils/validation.pyc in array2d(X, dtype, order, copy, force_all_finite)
     91     X_2d = np.asarray(np.atleast_2d(X), dtype=dtype, order=order)
     92     if force_all_finite:
---> 93         _assert_all_finite(X_2d)
     94     if X is X_2d and copy:
     95         X_2d = safe_copy(X_2d)

/usr/local/lib/python2.7/dist-packages/sklearn/utils/validation.pyc in _assert_all_finite(X)
     25     if (X.dtype.char in np.typecodes['AllFloat'] and not np.isfinite(X.sum())
     26             and not np.isfinite(X).all()):
---> 27         raise ValueError("Array contains NaN or infinity.")
     28 
     29 

ValueError: Array contains NaN or infinity.

数据矩阵中没有infs或nans ......可能导致这种行为的原因是什么？

编辑：显然我是not the only one。

Answer 1

这看起来像RBM中的数值稳定性错误。你可以用你的脚本打开github issue吗？

编辑：顺便提一下，如果您感兴趣，可以尝试通过在np.isfinite()方法的内部循环中添加_fit检查来查找问题的根源。 BernoulliRBM班。

Answer 2

此问题通常由两个因素引起。数据的初始缩放不正确。首先，输入数据需要绑定在0和1之间。记住RBM最初只是为二进制数据设计的。其次，学习率可能太高。 RBM代码的默认值通常基于MNIST数字识别数据集，该数据集可以处理更大的学习速率。

所以我会相信sklearn的实现，但不是基于默认值不适合当前数据集的新数据集的算法的稳定性。添加无穷大检查不会帮助您仍然需要调整学习率。

这就是为什么深度学习被认为是一种艺术，你可能还需要玩弄gibs样本的数量，miniatch的大小和动量。不要放弃，奖励大多是值得的。 Further reading

sklearn 0.14.1 RBM在没有NaN或Inf的情况下死亡

2 个答案: