class定义basic block(self, in_channels, out_channels, stride=1)模块之后如何放到def MEAN_Spot(opt): # channel 1 inputs1 = layers.Input(shape=(42, 42, 1)) inputs2 = layers.Input(shape=(42, 42, 1)) inputs3 = layers.Input(shape=(42, 42, 1)) # merge 1 inputs = layers.Concatenate()([inputs1, inputs2, inputs3]) conv1 = layers.Conv2D(3, (7,7), padding='same', activation='relu', kernel_regularizer=l2(0.001))(inputs)后面

可以在`def MEAN_Spot(opt)`中直接调用定义好的`BasicBlock`类，具体方法是在`def MEAN_Spot(opt)`中实例化`BasicBlock`类，然后将实例化的对象作为一个层连接到`conv1`之后。具体代码实现如下：

class BasicBlock(keras.layers.Layer):
    def __init__(self, out_channels, kernel_size=3, strides=1):
        super(BasicBlock, self).__init__()
        self.conv1 = keras.layers.Conv2D(out_channels, kernel_size, strides=strides, padding='same')
        self.bn1 = keras.layers.BatchNormalization()
        self.relu = keras.layers.ReLU()
        self.conv2 = keras.layers.Conv2D(out_channels, kernel_size, strides=1, padding='same')
        self.bn2 = keras.layers.BatchNormalization()
        if strides != 1:
            self.downsample = keras.Sequential([
                keras.layers.Conv2D(out_channels, 1, strides=strides),
                keras.layers.BatchNormalization()
            ])
        else:
            self.downsample = lambda x: x

    def call(self, inputs, training=False):
        identity = inputs

        x = self.conv1(inputs)
        x = self.bn1(x, training=training)
        x = self.relu(x)

        x = self.conv2(x)
        x = self.bn2(x, training=training)

        identity = self.downsample(identity)

        x += identity
        x = self.relu(x)

        return x


def MEAN_Spot(opt):
    inputs1 = keras.layers.Input(shape=(42, 42, 1))
    inputs2 = keras.layers.Input(shape=(42, 42, 1))
    inputs3 = keras.layers.Input(shape=(42, 42, 1))
    inputs = keras.layers.Concatenate()([inputs1, inputs2, inputs3])
    conv1 = keras.layers.Conv2D(3, (7, 7), padding='same', activation='relu', kernel_regularizer=l2(0.001))(inputs)
    ba1 = BasicBlock(out_channels=64, kernel_size=3, strides=1)(conv1)
    ba2 = BasicBlock(out_channels=64, kernel_size=3, strides=1)(ba1)
    att = BasicBlock(out_channels=64, kernel_size=3, strides=1)(ba2)

    merged_conv = keras.layers.Conv2D(8, (5, 5), padding='same', activation='relu', kernel_regularizer=l2(0.1))(att)
    merged_pool = keras.layers.MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2, 2))(merged_conv)
    flat = keras.layers.Flatten()(merged_pool)
    flat_do = keras.layers.Dropout(0.2)(flat)
    outputs = keras.layers.Dense(1, activation='linear', name='spot')(flat_do)

    model = keras.models.Model(inputs=[inputs1, inputs2, inputs3], outputs=[outputs])
    model.compile(loss={'spot': 'mse'}, optimizer=opt, metrics={'spot': tf.keras.metrics.MeanAbsoluteError()})

    return model