Nolearn 在 运行 分类时引发索引错误,但在回归时不会

Nolearn raises an index error when running a classification, but not with regression

我几天前就被我要描述的问题困住了。我正在关注 Daniel Nouri 关于深度学习的教程:http://danielnouri.org/notes/category/deep-learning/ 并且我尝试将他的示例改编为分类数据集。我这里的问题是,如果我将数据集视为回归问题,它会正常工作,但如果我尝试执行分类,它就会失败。我试着写了 2 个可重现的例子。

1) 回归(效果很好)

import lasagne
from sklearn import datasets
import numpy as np
from lasagne import layers
from lasagne.updates import nesterov_momentum
from nolearn.lasagne import NeuralNet
from sklearn.preprocessing import StandardScaler

iris = datasets.load_iris()
X = iris.data[iris.target<2]  # we only take the first two features.
Y = iris.target[iris.target<2]
stdscaler = StandardScaler(copy=True, with_mean=True, with_std=True)
X = stdscaler.fit_transform(X).astype(np.float32)
y = np.asmatrix((Y-0.5)*2).T.astype(np.float32)

print X.shape, type(X)
print y.shape, type(y)

net1 = NeuralNet(
    layers=[  # three layers: one hidden layer
        ('input', layers.InputLayer),
        ('hidden', layers.DenseLayer),
        ('output', layers.DenseLayer),
        ],
    # layer parameters:
    input_shape=(None, 4),  # 96x96 input pixels per batch
    hidden_num_units=10,  # number of units in hidden layer
    output_nonlinearity=None,  # output layer uses identity function
    output_num_units=1,  # 1 target value

    # optimization method:
    update=nesterov_momentum,
    update_learning_rate=0.01,
    update_momentum=0.9,

    regression=True,  # flag to indicate we're dealing with regression problem
    max_epochs=400,  # we want to train this many epochs
    verbose=1,
    )

net1.fit(X, y)

2)分类(会引发矩阵维数错误,我贴在下面)

import lasagne
from sklearn import datasets
import numpy as np
from lasagne import layers
from lasagne.nonlinearities import softmax
from lasagne.updates import nesterov_momentum
from nolearn.lasagne import NeuralNet
from sklearn.preprocessing import StandardScaler

iris = datasets.load_iris()
X = iris.data[iris.target<2]  # we only take the first two features.
Y = iris.target[iris.target<2]
stdscaler = StandardScaler(copy=True, with_mean=True, with_std=True)
X = stdscaler.fit_transform(X).astype(np.float32)
y = np.asmatrix((Y-0.5)*2).T.astype(np.int32)

print X.shape, type(X)
print y.shape, type(y)

net1 = NeuralNet(
    layers=[  # three layers: one hidden layer
        ('input', layers.InputLayer),
        ('hidden', layers.DenseLayer),
        ('output', layers.DenseLayer),
        ],
    # layer parameters:
    input_shape=(None, 4),  # 96x96 input pixels per batch
    hidden_num_units=10,  # number of units in hidden layer
    output_nonlinearity=softmax,  # output layer uses identity function
    output_num_units=1,  # 1 target value

    # optimization method:
    update=nesterov_momentum,
    update_learning_rate=0.01,
    update_momentum=0.9,

    regression=False,  # flag to indicate we're dealing with classification problem
    max_epochs=400,  # we want to train this many epochs
    verbose=1,
    )

net1.fit(X, y)

我使用代码 2 得到的失败输出。

(100, 4) <type 'numpy.ndarray'>
(100, 1) <type 'numpy.ndarray'>
  input                 (None, 4)               produces       4 outputs
  hidden                (None, 10)              produces      10 outputs
  output                (None, 1)               produces       1 outputs
---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-13-184a45e5abaa> in <module>()
     40     )
     41 
---> 42 net1.fit(X, y)

/Users/ivanvallesperez/anaconda/lib/python2.7/site-packages/nolearn/lasagne/base.pyc in fit(self, X, y)
    291 
    292         try:
--> 293             self.train_loop(X, y)
    294         except KeyboardInterrupt:
    295             pass

/Users/ivanvallesperez/anaconda/lib/python2.7/site-packages/nolearn/lasagne/base.pyc in train_loop(self, X, y)
    298     def train_loop(self, X, y):
    299         X_train, X_valid, y_train, y_valid = self.train_test_split(
--> 300             X, y, self.eval_size)
    301 
    302         on_epoch_finished = self.on_epoch_finished

/Users/ivanvallesperez/anaconda/lib/python2.7/site-packages/nolearn/lasagne/base.pyc in train_test_split(self, X, y, eval_size)
    399                 kf = KFold(y.shape[0], round(1. / eval_size))
    400             else:
--> 401                 kf = StratifiedKFold(y, round(1. / eval_size))
    402 
    403             train_indices, valid_indices = next(iter(kf))

/Users/ivanvallesperez/anaconda/lib/python2.7/site-packages/sklearn/cross_validation.pyc in __init__(self, y, n_folds, shuffle, random_state)
    531         for test_fold_idx, per_label_splits in enumerate(zip(*per_label_cvs)):
    532             for label, (_, test_split) in zip(unique_labels, per_label_splits):
--> 533                 label_test_folds = test_folds[y == label]
    534                 # the test split can be too big because we used
    535                 # KFold(max(c, self.n_folds), self.n_folds) instead of

IndexError: too many indices for array

这是怎么回事?我在做坏事吗?我想我尝试了一切,但我无法弄清楚发生了什么。

请注意,我今天刚刚使用以下命令更新了千层面和依赖项:pip install -r https://raw.githubusercontent.com/dnouri/kfkd-tutorial/master/requirements.txt

提前致谢

编辑

我通过执行后续更改实现了它的工作,但我仍然有一些疑问:

我还尝试将成本函数更改为 ROC-AUC。我知道有一个名为 objective_loss_function 的参数,默认情况下定义为 objective_loss_function=lasagne.objectives.categorical_crossentropy 但是......我如何使用 ROC AUC 作为成本函数而不是分类交叉熵?

谢谢

在 nolearn 中,如果你进行 class化,output_num_units 就是你有多少 classes。虽然可以仅使用一个输出单元实现两个 class class 化,但在 nolearn 中并没有以这种方式进行特殊处理,例如 [1]:

    if not self.regression:
        predict = predict_proba.argmax(axis=1)

请注意,无论您有多少 classes,预测始终是 argmax(这意味着两个 class classification 有两个输出,而不是一个)。

因此您的更改是正确的:output_num_units 应该始终是您拥有的 classes 的数量,即使您有两个,并且 Y 的形状应该是 (num_samples)(num_samples, 1) 包含代表类别的整数值,而不是,例如,每个类别都有一个具有形状 (num_samples, num_categories).

的向量

回答你的另一个问题,Lasagne 似乎没有 ROC-AUC objective,所以你需要实现它。请注意,您不能使用 scikit-learn 的实现,例如,因为 Lasagne 需要 objective 函数将 theano 张量作为参数,而不是列表或 ndarrays。要了解如何在 Lasagne 中实现 objective 函数,您可以查看现有的 objective 函数 [2]。他们中的许多人都参考了 theano 内部的那些,你可以在 [3] 中看到他们的实现(它会自动滚动到 binary_crossentropy,这是 objective 函数的一个很好的例子)。

[1] https://github.com/dnouri/nolearn/blob/master/nolearn/lasagne/base.py#L414

[2] https://github.com/Lasagne/Lasagne/blob/master/lasagne/objectives.py

[3] https://github.com/Theano/Theano/blob/master/theano/tensor/nnet/nnet.py#L1809