卷积神经网络中的形状误差

时间:2018-12-10 21:31:35

标签: python machine-learning keras neural-network conv-neural-network

我正在尝试训练具有以下结构的神经网络:

model = Sequential()

model.add(Conv1D(filters = 300, kernel_size = 5, activation='relu', input_shape=(4000, 1)))
model.add(Conv1D(filters = 300, kernel_size = 5, activation='relu'))
model.add(MaxPooling1D(3))
model.add(Conv1D(filters = 320, kernel_size = 5, activation='relu'))
model.add(MaxPooling1D(3))
model.add(Dropout(0.5))

model.add(Dense(num_labels, activation='softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

return model

我收到此错误:

expected dense_1 to have shape (442, 3) but got array with shape (3, 1)

我的输入是一组短语(总共12501个),它们已针对4000个最相关的单词进行了标记,并且有3种可能的分类。因此,我的输入是train_x.shape =(12501,4000)。我将其重塑为Conv1D层的(12501,4000,1)。现在,我的train_y.shape =(12501,3),然后将其重塑为(12501,3,1)。

我正在使用fit函数,如下所示:

model.fit(train_x, train_y, batch_size=32, epochs=10, verbose=1, validation_split=0.2, shuffle=True)

我在做什么错了?

1 个答案:

答案 0 :(得分:1)

无需转换标签形状即可进行分类。然后您可以查看您的网络结构。

print(model.summary())
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d_1 (Conv1D)            (None, 3996, 300)         1800      
_________________________________________________________________
conv1d_2 (Conv1D)            (None, 3992, 300)         450300    
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 1330, 300)         0         
_________________________________________________________________
conv1d_3 (Conv1D)            (None, 1326, 320)         480320    
_________________________________________________________________
max_pooling1d_2 (MaxPooling1 (None, 442, 320)          0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 442, 320)          0         
_________________________________________________________________
dense_1 (Dense)              (None, 442, 3)            963       
=================================================================
Total params: 933,383
Trainable params: 933,383
Non-trainable params: 0
_________________________________________________________________

模型的最后输出是(None, 442, 3),但是标签的形状是(None, 3, 1)。您最终应该最终在全局池层GlobalMaxPooling1D()或展平层Flatten()中结束,将3D输出转换为2D输出,以进行分类或回归。