kerasで作ったモデルをcoremltoolsでmlmodelに変換しようとした際でたエラーを解決したいです

元のモデルは以下のようなモデルです

def wavenetModel(input_size) :
    filter_count = 10
    output_count = 1
    def residual_block(i, j):
        def f(x):
            original_x = x
            tanh_out = Conv1D(filter_count, kernel_size=2,
                              strides=1, padding="causal",
                              dilation_rate=2**j, use_bias=False, 
                              kernel_regularizer=l2(0.))(x)
            tanh_out = Activation("tanh")(tanh_out)
            sigm_out = Conv1D(filter_count, kernel_size=2,
                              strides=1, padding="causal",
                              dilation_rate=2**j, use_bias=False, 
                              kernel_regularizer=l2(0.))(x)
            sigm_out = Activation("sigmoid")(sigm_out)
            x = Multiply()([tanh_out, sigm_out])
            res_x = Conv1D(filter_count, 1, padding="same", use_bias=False,
                           kernel_regularizer=l2(0.))(x)
            skip_x = Conv1D(filter_count, 1, padding="same", use_bias=False,
                            kernel_regularizer=l2(0.))(x)
            res_x = Add()([original_x, res_x])
            return res_x, skip_x
        return f
    input = Input(shape=(input_size,))
    out = input
    out = Reshape((input_size, 1))(out)
    skip_connections = []
    out = Conv1D(filter_count, 2, dilation_rate=1, padding="causal")(out)
    for i in range(4):
        for j in range(0, 9+1):
            out, skip_out = residual_block(i, j)(out)
            skip_connections.append(skip_out)
    out = Add()(skip_connections)
    out = Activation("relu")(out)
    out = Conv1D(filter_count, 1, padding="same", kernel_regularizer=l2(0.))(out)
    out = Activation("relu")(out)
    out = Conv1D(filter_count, 1, padding="same")(out)
    out = Conv1D(output_count, 1, padding="same", activation="tanh")(out)
    out = Flatten()(out)
    model = Model(input, out)
    return model

これを保存したh5ファイルをcoremltoolsを使ってmlmodelに変換しようとした際

/.pyenv/versions/3.6.2/lib/python3.6/site-packages/coremltools/models/model.py:109: RuntimeWarning: You will not be able to run predict() on this Core ML model.Underlying exception message was: Error compiling model: "Error reading protobuf spec. validator error: Layer 'conv1d_3__causal_pad__' produces an output named 'conv1d_1_output__causal_pad__' which is also an output produced by the layer 'conv1d_2__causal_pad__'.".
  RuntimeWarning)

とのエラーが表示されます
解決方法をお教えください。