How to combine two predefined models in Keras TensorFlow?

Question

I want to build a neural network that has two inputs and uses EfficientNetB1 to extract features and fine-tune on new layers, so I wrote this code:

def createNet(self,shape):
    FE1 = K.applications.EfficientNetB1(include_top=False, input_shape=shape)
    FE2 = K.applications.EfficientNetB1(include_top=False, input_shape=shape)
    inp1 = FE1.input
    out1 = FE1.layers[-1].output
    inp2 = FE2.input
    out2 = FE2.layers[-1].output

    merged_out = K.layers.concatenate((out1, out2))
    # .... other layers
    self.model = K.models.Model(inputs=[inp1, inp2], outputs=[merged_out])
    
    self.model.summary()

But I got this error:

ValueError: The name "stem_conv_pad" is used 2 times in the model. All layer names should be unique.

So how can I build my model?

Answer 1

Base on this I added below codes to solve it.

for layer in FE2.layers:
    layer._name = layer.name + str("_2")