如何将自定义路缘石层与多个输出连接起来

使用keras api模式可以创建任何网络体系结构。 在你的情况下,一个可能的解决方案是

input_layer = Input(shape=(100,1))
custom_layer = Dense(10)(input_layer)

# layer A model
layer_a = Dense(10, activation='relu')(custom_layer)
output1 = Dense(1, activation='sigmoid')(layer_a)

# layer B model
layer_b = Dense(10, activation='relu')(custom_layer)
output1 = Dense(1, activation='sigmoid')(layer_b)

# define model input and output
model = Model(inputs=input_layer, outputs=[output1, output2])

如果自定义层在一个输入上应用时有两个输出张量(即返回输出张量列表),则:

custom_layer_output = CustomLayer(...)(input_tensor)

layer_a_output = LayerA(...)(custom_layer_output[0])
layer_b_output = LayerB(...)(custom_layer_output[1])

但如果它应用于两个不同的输入张量,则:

custom_layer = CustomLayer(...)
out1 = custom_layer(input1)
out2 = custom_layer(input2)

layer_a_output = LayerA(...)(out1)
layer_b_output = LayerB(...)(out2)

# alternative way
layer_a_output = LayerA(...)(custom_layer.get_output_at(0))
layer_b_output = LayerB(...)(custom_layer.get_output_at(1))

merge ,这将很快更新文档。 基本思想是使用列表。每一个你必须重新在你的自定义层(像层和形状)你必须返回他们的列表。

output_1, output_2 = custom_layer()(input_layer)
layer_a_output = layer_a()(output_1)
layer_b_output = layer_b()(output_2)