python - 使用 Tensorflow 2.0 中的层子类化在我的自定义层中出现此错误 "The first argument to ` Layer.call` 必须始终通过。”

Question

我使用 Tensorflow 2.0 图层子类化使用图层制作了这个自定义图层。我正在尝试制作一层残留块。但是当我通过顺序 API 在我的模型中添加这个自定义层时，我得到了
下面的错误。

class ResidualBlock(Layer):

    def __init__(self, **kwargs):
        super(ResidualBlock, self).__init__(**kwargs)

    def build(self, input_shape):
        """
        This method should build the layers according to the above specification. Make sure 
        to use the input_shape argument to get the correct number of filters, and to set the
        input_shape of the first layer in the block.
        """
        self.bn_1 = BatchNormalization(input_shape=input_shape)
        self.conv_1 = Conv2D( input_shape[0],(3,3), padding='SAME')
        self.bn_2 = BatchNormalization()
        self.conv_2 = Conv2D( input_shape[0],(3,3), padding='SAME')






    def call(self, inputs, training=False):
        """
        This method should contain the code for calling the layer according to the above
        specification, using the layer objects set up in the build method.
        """
        h = self.bn_1(training=True)(inputs)
        h = tf.nn.relu(h)
        h = self.conv_1(h)
        h = self.bn_2(training=True)(h)
        h = tf.nn.relu(h)
        h = self.conv_2(h)
        return Add(inputs, h)

但是当我初始化这个层时，我收到了错误。

test_model = tf.keras.Sequential([ResidualBlock(input_shape=(28, 28, 1), name="residual_block")])
test_model.summary()

我的错误日志:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-13-991ed1d78e4b> in <module>()
      1 # Test your custom layer - the following should create a model using your layer
      2 
----> 3 test_model = tf.keras.Sequential([ResidualBlock(input_shape=(28, 28, 1), name="residual_block")])
      4 test_model.summary()

5 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/impl/api.py in wrapper(*args, **kwargs)
    263       except Exception as e:  # pylint:disable=broad-except
    264         if hasattr(e, 'ag_error_metadata'):
--> 265           raise e.ag_error_metadata.to_exception(e)
    266         else:
    267           raise

ValueError: in user code:

    <ipython-input-12-3beea3ca10b0>:32 call  *
        h = self.bn_1(training=True)(inputs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py:800 __call__  **
        'The first argument to `Layer.call` must always be passed.')

    ValueError: The first argument to `Layer.call` must always be passed.

Answer 1

在调用方法期间将批规范的前向传递更改为 h=self.bn_1(inputs) .既然你路过 training=True对于整个层，tensorflow 将自动负责为其所有子层维护相同的标志，并且您不需要为每个子层明确传递它。但是，如果您的应用程序希望以与其他层不同的方式控制批处理规范，请使用 h=self.bn_1(inputs, training=True) .并且您的最终 return 语句格式不正确，应该类似于 Add()([inputs, h])

class ResidualBlock(Layer):

    def __init__(self, **kwargs):
        super(ResidualBlock, self).__init__(**kwargs)

    def build(self, input_shape):
        """
        This method should build the layers according to the above specification. Make sure 
        to use the input_shape argument to get the correct number of filters, and to set the
        input_shape of the first layer in the block.
        """
        self.bn_1 = BatchNormalization(input_shape=input_shape)
        self.conv_1 = Conv2D(input_shape[3],(3,3), padding='SAME')
        self.bn_2 = BatchNormalization()
        self.conv_2 = Conv2D(input_shape[3],(3,3), padding='SAME')

    def call(self, inputs, training=False):
        """
        This method should contain the code for calling the layer according to the above
        specification, using the layer objects set up in the build method.
        """
        h = self.bn_1(inputs)
        h = tf.nn.relu(h)
        h = self.conv_1(h)
        h = self.bn_2(h)
        h = tf.nn.relu(h)
        h = self.conv_2(h)
        return Add()([inputs, h])

pk = ResidualBlock()
model = tf.keras.Sequential([pk])
model(tf.ones((1, 28, 28, 3)))

因此，一旦使用 tf.ones() 的示例输入调用您的模型，将调用 build 以创建批处理规范和卷积层。对于 conv 层，您通过索引到最后一个维度来使用与输入相同的过滤器数量