AttributeError: 'Flatten' object 没有属性 'shape'

Question

我是 TensorFlow 的新手，正在尝试使用tf.keras.layers ZDB974Z4A2387183CACEF68F5399D8CZ 实现 CNN model 这是我试图实现的代码。

def convolutional_model(input_shape):
    input_img = tf.keras.Input(shape=input_shape)
    Z1 = tf.keras.layers.Conv2D(filters = 16 , kernel_size= (4,4), strides = (1,1), padding='same')(input_img)
    A1 = tf.keras.layers.ReLU()
    P1 = tf.keras.layers.MaxPool2D(pool_size=(8,8), strides=(8, 8), padding='same')
    Z2 = tf.keras.layers.Conv2D(filters = 16 , kernel_size= (2,2), strides = (1,1), padding='same')(input_img)
    A2 = tf.keras.layers.ReLU()
    P2 = tf.keras.layers.MaxPool2D(pool_size=(4,4), strides=(4, 4), padding='valid')
    F = tf.keras.layers.Flatten()
    outputs = tf.keras.layers.Dense(units=6, activation='softmax')(F)

    model = tf.keras.Model(inputs=input_img, outputs=outputs)
    return model

当我尝试运行它时，我收到以下错误：

AttributeError                            Traceback (most recent call last)
<ipython-input-66-12f400853748> in convolutional_model(input_shape)
     43     P2 = tf.keras.layers.MaxPool2D(pool_size=(4,4), strides=(4, 4), padding='valid')
     44     F = tf.keras.layers.Flatten()
---> 45     outputs = tf.keras.layers.Dense(units=6, activation='softmax')(F)
     46 
     47     # YOUR CODE ENDS HERE

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    980       with ops.name_scope_v2(name_scope):
    981         if not self.built:
--> 982           self._maybe_build(inputs)
    983 
    984         with ops.enable_auto_cast_variables(self._compute_dtype_object):

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _maybe_build(self, inputs)
   2616     if not self.built:
   2617       input_spec.assert_input_compatibility(
-> 2618           self.input_spec, inputs, self.name)
   2619       input_list = nest.flatten(inputs)
   2620       if input_list and self._dtype_policy.compute_dtype is None:

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    164         spec.min_ndim is not None or
    165         spec.max_ndim is not None):
--> 166       if x.shape.ndims is None:
    167         raise ValueError('Input ' + str(input_index) + ' of layer ' +
    168                          layer_name + ' is incompatible with the layer: '

AttributeError: 'Flatten' object has no attribute 'shape'

当我用input_img替换F时，function 运行没有任何错误，但这不是我想要的 output。 有人可以帮我解决这个问题吗？

Answer 1

Keras 功能 API旨在让您将 model 的前一层作为输入传递到下一层。 对于您定义的大多数层，您并没有真正这样做，而是使它们成为彼此不连接的独立层。 要将一层的结果传递给另一层，您需要通过传入上一层来调用该层。 例如，您的意思可能是这样的。

Z1 = tf.keras.layers.Conv2D(filters = 16 , kernel_size= (4,4), strides = (1,1), padding='same')(input_img)
A1 = tf.keras.layers.ReLU()(Z1)