千层面函数参数的形状不正确

Question

我正在尝试使用scikit-neuralnetwork库构建神经网络回归器。

据我了解，NY NN似乎正在建设很好，但我一直运行到下面的错误在nn.predict()电话：

rmichael@node:~/Sandbox$ sudo python NNScript.py 
Traceback (most recent call last): 
    File "NNScript.py", line 15, in <module> 
    print nn.predict(X_train[0]) 
    File "https://stackoverflow.com/users/rmichael/scikit-neuralnetwork/sknn/mlp.py", line 309, in predict 
    return super(Regressor, self)._predict(X) 
    File "https://stackoverflow.com/users/rmichael/scikit-neuralnetwork/sknn/mlp.py", line 256, in _predict 
    return self._backend._predict_impl(X) 
    File "https://stackoverflow.com/users/rmichael/scikit-neuralnetwork/sknn/backend/lasagne/mlp.py", line 242, in _predict_impl 
    return self.f(X) 
    File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 786, in __call__ 
    allow_downcast=s.allow_downcast) 
    File "/usr/local/lib/python2.7/dist-packages/theano/tensor/type.py", line 177, in filter 
    data.shape)) 
TypeError: ('Bad input argument to theano function with name "https://stackoverflow.com/users/rmichael/scikit-neuralnetwork/sknn/backend/lasagne/mlp.py:199" at index 0(0-based)', 'Wrong number of dimensions: expected 2, got 1 with shape (59,).') 
rmichael@node:~/Sandbox$ 

我的代码如下：

import numpy as np 
from sknn.mlp import Regressor, Layer 

X_train = np.genfromtxt("OnlineNewsPopularity.csv", dtype=float, delimiter=',', skip_header=1, usecols=range(1,60)) 
y_train = np.genfromtxt("OnlineNewsPopularity.csv", dtype=float, delimiter=',', names=True, usecols=(60)) 

nn = Regressor(
    layers=[ 
     Layer("Rectifier", units=1), 
     Layer("Linear")], 
    learning_rate=0.02, 
    n_iter=1) 
nn.fit(X_train, y_train) 

print nn.predict(X_train[0]) 

这里可能有人知道这里出了什么问题？任何帮助将不胜感激。

Answer 1

问题是，模型期望它的输入是一个矩阵，但你提供一个向量。

在行

print nn.predict(X_train[0]) 

你为什么只通过的X_train第一排？

我希望，如果你通过了整个矩阵，即

print nn.predict(X_train) 

左右，它是作为一个矩阵通过只有一行堆叠的第一行：

print nn.predict(np.expand_dims(X_train[0], 0)) 

那么它可以按预期工作。