Keras加载模型和连接无法正常工作

Question

我正在从Keras加载一个预先创建的模型，并且形状有些问题。当我按以下方式加载模型

neuruleModelPath = "model/diabetes/neurules_model.h5"
neuruleLoadedModel = load_model(neuruleModelPath)

并检查print(neuruleLoadedModel.summary())输出的内容是：

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input (InputLayer)              (None, 24)           0                                            
__________________________________________________________________________________________________
neurules (Dense)                (None, 20)           500         input[0][0]                      
__________________________________________________________________________________________________
signumAfterNeurules (Lambda)    (None, 20)           0           neurules[0][0]                   
__________________________________________________________________________________________________
layer_split0 (Lambda)           (None, 11)           0           signumAfterNeurules[0][0]        
__________________________________________________________________________________________________
layer_split1 (Lambda)           (None, 9)            0           signumAfterNeurules[0][0]        
__________________________________________________________________________________________________
or0 (Lambda)                    (None, 1)            0           layer_split0[0][0]               
__________________________________________________________________________________________________
or1 (Lambda)                    (None, 1)            0           layer_split1[0][0]               
__________________________________________________________________________________________________
output (Lambda)                 (None, 2)            0           or0[0][0]                        
                                                                 or1[0][0]                        
==================================================================================================
Total params: 500
Trainable params: 0
Non-trainable params: 500
__________________________________________________________________________________________________

所以一切似乎都很好，我的输出形状为2，所以(None,2)似乎还可以，因为正在考虑“批处理”。问题是，当我尝试将模型加载为一层时（它需要进入另一个模型的中间），如下所示：

#this is the input tensor
inputs = Input(shape=(inputSize,), name='main_input')
#normal network
x_up = Dense(hiddenNeuronsQt, activation='softsign', name="classic_network")(inputs)
#neurule network
neuruleNetwork = neuruleLoadedModel(inputs)

#concatenating/merging them
merged = concatenate([x_up, neuruleNetwork], name='merging_layer')

#this is the only layer after concatenating/merge
x = Dense(hiddenNeuronsQt, activation='softsign', name='layer_after_merge')(merged)
#this is the output layer
y = Dense(outputSize, activation='softsign', name='output_layer')(x)

concatenate()引发错误：

InvalidArgumentError: Shape must be rank 2 but is rank 1 for 'merging_layer_10/concat' (op: 'ConcatV2') with input shapes: [?,16], [2], [].

如果我检查neuruleNetwork.shape会给我(2,)，但是当我直接用neuruleLoadedModel.summary()检查原始加载的模型时，最后一层会给我{{1} }。

我应该如何进行合并才能在那里合并？

编辑： 可能我的问题实际上是在我的原始模型中，在加载之前，我创建了这样的图层：

(None, 2)

如果我将第def signumTransform(x): """ SIGNUM function if positive 1 if negative -1 """ import keras.backend return keras.backend.sign(x) def logical_or_layer(x): """Processing an OR operation""" import keras.backend #normalized to 0,1 aux_array = keras.backend.sign(x) aux_array = keras.backend.relu(aux_array) # OR operation aux_array = keras.backend.any(aux_array) # casting back the True/False to 1,0 aux_array = keras.backend.cast(aux_array, dtype='float32') return aux_array #this is the input tensor inputs = Input(shape=(inputSize,), name='input') #this is the Neurule layer x = Dense(neurulesQt, activation='softsign', name='neurules')(inputs) #after each neuron layer, the outputs need to be put into SIGNUM (-1 or 1) x = Lambda(signumTransform, output_shape=lambda x:x, name='signumAfterNeurules')(x) #separating into 2 (2 possible outputs) layer_split0 = Lambda( lambda x: x[:, :11], output_shape=[11], name='layer_split0')(x) layer_split1 = Lambda( lambda x: x[:, 11:20], output_shape=[9], name='layer_split1')(x) #this is the OR layer y_0 = Lambda(logical_or_layer, output_shape=[1], name='or0')(layer_split0) y_1 = Lambda(logical_or_layer, output_shape=[1], name='or1')(layer_split1) y = Lambda(lambda x: K.stack([x[0], x[1]]),output_shape=[2], name="output")([y_0, y_1]) 层用作输出，没问题，但是当我尝试使用layer_split0时，它不再起作用了，我的意思是，如果加载它，模型本身就可以工作，不再。在函数y_0中，我可能做错了，但我无法弄清楚。