沿單個特徵行的Keras卷積

Question

我有一個多類分類問題。說我有一個特徵矩陣：

A B C D 
1 -1 1 -6 
2 0.5 0 11 
7 3.7 1 1 
4 -50 1 0 

和標籤：

LABEL 
0 
1 
2 
0 
2 

我想嘗試一起Keras每個單一特徵行應用於卷積核。說nb_filter = 2和batch_size = 3。所以我期望卷積層的輸入形狀爲（3,4），輸出形狀爲（3,3）（因爲它適用於AB，BC，CD）。

這裏是我的嘗試與Keras（V1.2.1，Theano後端）：

def CreateModel(input_dim, num_hidden_layers): 
    from keras.models import Sequential 
    from keras.layers import Dense, Dropout, Convolution1D, Flatten 

    model = Sequential() 
    model.add(Convolution1D(nb_filter=10, filter_length=1, input_shape=(1, input_dim), activation='relu')) 
    model.add(Dense(3, activation='softmax')) 
    model.compile(loss='categorical_crossentropy', optimizer='adam') 
    model.summary() 
    return model 

def OneHotTransformation(y): 
    from keras.utils import np_utils 
    return np_utils.to_categorical(y) 

X_train = X_train.values.reshape(X_train.shape[0], 1, X_train.shape[1]) 
X_test = X_test.values.reshape(X_test.shape[0], 1, X_test.shape[1]), 
y_train = OneHotTransformation(y_train) 

clf = KerasClassifier(build_fn=CreateModel, input_dim=X_train.shape[1], num_hidden_layers=1, nb_epoch=10, batch_size=500) 

clf.fit(X_train, y_train) 

形狀：

print X_train.shape 
print X_test.shape 
print y_train.shape 

輸出：

(45561, 44) 
(11391, 44) 
(45561L,) 

當我嘗試運行此我得到的代碼和例外：

ValueError: Error when checking model target: expected dense_1 to have 3 dimensions, but got array with shape (45561L, 3L) 

我試圖重塑y_train：

y_train = y_train.reshape(y_train.shape[0], 1, y_train.shape[1]) 

這讓我異常：

ValueError: Error when checking model target: expected dense_1 to have 3 dimensions, but got array with shape (136683L, 2L) 

1. 是這種做法與Convolution1D正確實現我的目標是什麼？
2. 如果＃1是，我該如何解決我的代碼？

我已經閱讀了很多github問題和一些問題（1，2），但它並沒有真正的幫助。

謝謝。

UPDATE1： 根據Matias Valdenegro的評論。 下面是重塑 'X' 之後和 'Y' onehot編碼後的形狀：

print X_train.shape 
print X_test.shape 
print y_train.shape 

輸出：

(45561L, 1L, 44L) 
(11391L, 1L, 44L) 
(45561L, 3L) 

UPDATE2：再次由於Matias的Valdenegro。確定它是一個複製粘貼問題後，重新塑形是在創建模型後完成的。代碼應該如下所示：

def CreateModel(input_dim, num_hidden_layers): 
    from keras.models import Sequential 
    from keras.layers import Dense, Dropout, Convolution1D, Flatten 

    model = Sequential() 
    model.add(Convolution1D(nb_filter=10, filter_length=1, input_shape=(1, input_dim), activation='relu')) 
    model.add(Dense(3, activation='softmax')) 
    model.compile(loss='categorical_crossentropy', optimizer='adam') 
    model.summary() 
    return model 

def OneHotTransformation(y): 
    from keras.utils import np_utils 
    return np_utils.to_categorical(y) 

clf = KerasClassifier(build_fn=CreateModel, input_dim=X_train.shape[1], num_hidden_layers=1, nb_epoch=10, batch_size=500) 

X_train = X_train.values.reshape(X_train.shape[0], 1, X_train.shape[1]) 
X_test = X_test.values.reshape(X_test.shape[0], 1, X_test.shape[1]), 
y_train = OneHotTransformation(y_train) 

clf.fit(X_train, y_train) 

Answer 1

1D卷積的輸入應該有尺寸（num_samples，channels，width）。所以這意味着你需要重塑X_train和X_test，而不是y_train：

X_train = X_train.reshape(X_train.shape[0], 1, X_train.shape[1]) 
X_test = X_test.reshape(X_test.shape[0], 1, X_test.shape[1])