Keras-使用卷积网的形状不匹配

我以以下方式构建了我的keras模型(这当然不是最终的生产就绪模型):

self.model = Sequential()        
self.model.add(Conv2D(32, (3, 3), input_shape=(674, 514, 1), padding='same', 
activation='relu'))
self.model.compile(loss='mean_squared_error', optimizer='adam', metrics=
['accuracy'])

模型摘要为:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 674, 514, 32)      320       
=================================================================
Total params: 320
Trainable params: 320
Non-trainable params: 0
_________________________________________________________________

我尝试以以下方式进行调整:

self.model.fit(self.input_images, self.output_images, batch_size=32, 
epochs=10, verbose=1, shuffle=True)

培训输入和输出的形状( self.input_images, self.output_images )都是 (100, 674, 514, 1) .

当我尝试训练我的模型时,我得到以下例外:

ValueError: Error when checking target: expected conv2d_1 to have shape 
(674, 514, 32) but got array with shape (674, 514, 1)

非常感谢您的帮助。