当使用 Keras Function API 时,我们可以training = False在调用预训练模型时传递参数,如本教程所示。
如何在 Keras Sequential API 中实现相同的功能?
这是我尝试使用 Sequential API 复制的代码:
inputs = tf.keras.Input( shape = ( TARGET_SIZE[0], TARGET_SIZE[1], 3 ) )
base_model = Xception( include_top = False, pooling = 'avg' )
base_model.trainable = False
x = base_model( inputs, training = False )
x = Dense( 512, activation = 'relu' )( x )
x = Dense( 256, activation = 'relu' )( x )
x = Dense( 128, activation = 'relu' )( …Run Code Online (Sandbox Code Playgroud)