Create a custom regularizer on weights of 2 layers

Question

Here is small snippet of my code describing my custom regularizer that I want to implement.

# Code adapted from https://github.com/keras-team/keras/issues/5563

class CustomRegularization(Layer):
    def __init__(self, **kwargs):
        super(CustomRegularization, self).__init__(**kwargs)

    def call(self ,x ,mask=None):
        ld=x[0]
        rd=x[1]
        reg = K.dot(K.transpose(ld), rd)
        reg_norm = K.sqrt(K.sum(K.square(reg)))
        self.add_loss(reg_norm, x)
        return ld


    def compute_output_shape(self, input_shape):
        return (input_shape[0][0],input_shape[0][1])

def model():
    input1 = Input(shape=(224, 224, 3))
    input2 = Input(shape=(224, 224, 3))

    inp1 = Flatten()(input1)
    inp2 = Flatten()(input2)

    layer1 = Dense(1024, activation="sigmoid")
    x1_1 = layer1(inp1)
    x2_1 = layer1(inp2)

    layer2 = Dense(1024, activation="sigmoid")
    x1_2 = layer2(inp1)
    x2_2 = layer2(inp2)

    # get weights of layer1 and layer2

    layer1_wt = layer1.trainable_weights[0]
    layer2_wt = layer2.trainable_weights[0]

    # This is a regularization term on the weights of layer1 and layer2.
    regularization = CustomRegularization()([layer1_wt, layer2_wt])

    model = Model([input1, input2], [x1_2, x2_2, regularization])

if __name__ == "__main__":
    m = model()

This returns the error AttributeError: 'Variable' object has no attribute '_keras_history' and is not able to create the model. I know that this error would be because of incompatible outputs (since inputs are keras Input layer). [For more details refer to @fchollet's comment on issue #7362 ].

The main problem here are the layer1.trainable_weights[0] and layer2.trainable_weights[0]. These are tf.Variable (tensorflow variables) and not Keras Tensors. I would require them to convert to keras tensors. How do I do that?