构造AlexNet模型遇到的几个小问题

部分源码

x = tf.random.normal([1, 227, 227, 3])

alexnet = keras.Sequential([
    keras.layers.Conv2D(96, 11, 4, padding = "same"),
    keras.layers.ReLU(),
    keras.layers.MaxPooling2D((3,3),2),
    keras.layers.BatchNormalization(),
    
    keras.layers.Conv2D(256, 5, 1, padding = "same"),
    keras.layers.ReLU(),
    keras.layers.MaxPooling2D((3,3),2),
    keras.layers.BatchNormalization(),
    
    keras.layers.Conv2D(384, 3, 1, padding = "same"),
    keras.layers.ReLU(),
    
    keras.layers.Conv2D(128, 3, 4, padding = "same"),
    keras.layers.ReLU(),
    
    keras.layers.Flatten(),  #拉平
    keras.layers.Dense(4096),
    keras.layers.ReLU(),
    
    keras.layers.Dense(1000),
    keras.layers.Softmax()
])
# alexnet(x).shape

# alexnet.build(input_shape = [None, 227, 227, 3])            
alexnet.summary()

在输出模型遇到一个问题，报错如下：

This model has not yet been built. Build the model first by calling build() or calling fit() with some data, or specify an input_shape argument in the first layer(s) for automatic build.

解决：原因是没有构建模型的输入方式，建立方式如上文注释处，参数None是样本数。227,227,3是输入的大小