我正在接近神经网络实现,试图使用Theano构建一个可行的MLP . 在本教程之后,我尝试通过添加一个图层来增强网络,总共有两个隐藏层,每个层具有相同数量的单位(250) . 问题是当我运行脚本时遇到了"Shape mismatch" ValueError . 我的代码是教程代码的修改版本,可以在这里找到http://deeplearning.net/tutorial/mlp.html .
我修改的部分是片段-2,即MLP对象,如下所示:
class MLP(object):
def __init__(self, rng, input, n_in, n_hidden, n_out):
"""Initialize the parameters for the multilayer perceptron
:type rng: numpy.random.RandomState
:param rng: a random number generator used to initialize weights
:type input: theano.tensor.TensorType
:param input: symbolic variable that describes the input of the
architecture (one minibatch)
:type n_in: int
:param n_in: number of input units, the dimension of the space in
which the datapoints lie
:type n_hidden: int
:param n_hidden: number of hidden units
:type n_out: int
:param n_out: number of output units, the dimension of the space in
which the labels lie
"""
self.hiddenLayer1 = HiddenLayer(
rng=rng,
input=input,
n_in=n_in,
n_out=n_hidden,
activation=T.tanh
)
#try second hidden layer
self.hiddenLayer2 = HiddenLayer(
rng=rng,
input=self.hiddenLayer1.output,
n_in=n_in,
n_out=n_hidden,
activation=T.tanh
)
# The logistic regression layer gets as input the hidden units
# of the hidden layer
self.logRegressionLayer = LogisticRegression(
input=self.hiddenLayer2.output,
n_in=n_hidden,
n_out=n_out
)
# end-snippet-2 start-snippet-3
# L1 norm ; one regularization option is to enforce L1 norm to
# be small
self.L1 = (
abs(self.hiddenLayer1.W).sum()
+ abs(self.hiddenLayer2.W).sum()
+ abs(self.logRegressionLayer.W).sum()
)
# square of L2 norm ; one regularization option is to enforce
# square of L2 norm to be small
self.L2_sqr = (
(self.hiddenLayer1.W ** 2).sum()
+ (self.hiddenLayer2.W ** 2).sum()
+ (self.logRegressionLayer.W ** 2).sum()
)
# negative log likelihood of the MLP is given by the negative
# log likelihood of the output of the model, computed in the
# logistic regression layer
self.negative_log_likelihood = (
self.logRegressionLayer.negative_log_likelihood
)
# same holds for the function computing the number of errors
self.errors = self.logRegressionLayer.errors
# the parameters of the model are the parameters of the two layer it is
# made out of
self.params = self.hiddenLayer1.params + self.hiddenLayer2.params + self.logRegressionLayer.params
# end-snippet-3
# keep track of model input
self.input = input
我还删除了一些注释以便于阅读 . 我得到的输出错误是:
ValueError:形状不匹配:x有250列(和20行)但y有784行(和250列)应用导致错误的节点:Dot22(Elemwise {Composite {tanh((i0 i1))}} [(0 ,0)] . 0,W)输入类型:[TensorType(float64,matrix),TensorType(float64,matrix)]输入形状:[(20,250),(784,250)]输入步幅:[(2000, 8),(2000,8)]输入值:['未显示','未显示']
1 回答
第2层的输入大小需要与第1层的输出大小相同 .
hiddenLayer2
将hiddenLayer1
作为输入,hiddenLayer1.n_out == n_hidden
作为'hiddenLayer2.n_in == n_in' . 在这种情况下n_hidden == 250
和n_in == 784
. 它们应匹配但不会因此而产生错误 .解决方案是制作
hiddenLayer2.n_in == hiddenLayer1.n_out
.