几天前，我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/我试图将他的示例调整为分类数据集。我的问题是，如果我将数据集视为回归问题，它可以正常工作，但如果我尝试执行分类，它会失败。我试图写 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（它会引发矩阵维度的错误；我将其粘贴在下面）
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
这里发生了什么？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我的千层面和依赖项：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：
我将 Y 定义为具有 0/1 值的一维向量：
y = Y.astype(np.int32)但我仍然有一些疑问我不得不将参数更改
output_num_units=1为output_num_units=2，但我不确定是否理解这一点，因为我正在处理二进制分类问题，并且我认为这个多层感知器应该只有 1 个输出神经元，而不是其中的 2 个......我是错误的？
我还尝试将成本函数更改为 ROC-AUC。我知道有一个称为默认objective_loss_function定义的参数，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