網(wǎng)絡(luò)的結(jié)構(gòu)是這樣的：

#1st layer
model.add(Conv2D(20, 5, 5, activation='sigmoid', input_shape=(32, 32, 1)))
model.add(MaxPool2D(pool_size=(2, 2)))
#2nd layer
model.add(Conv2D(30, 5, 5, activation='sigmoid'))
model.add(MaxPool2D(pool_size=(2, 2)))
#fully connected layer
model.add(Flatten())
model.add(Dense(500, init='normal', activation='sigmoid'))
# model.add(Dropout(0.5))
# model.add(Dense(10, activation='sigmoid'))
#model.add(Reshape((-1, 5)))
model.add(Dense(5, init='normal', activation='softmax'))

調(diào)用網(wǎng)絡(luò)時：

model.fit(x=traindata, y=trainlabel, batch_size=16, nb_epoch=15, shuffle=True, verbose=1, validation_data=(testdata, testlabel))

報錯是這個：
ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (500, 5)

然后x向量為4維的圖片信息，y向量為圖片的標(biāo)簽，他們的shape分別是(500, 32, 32, 1)，(500, 5)，就是不懂為什么y向也需要是4維的呢