How to use the autokeras.Merge function in autokeras

def test_merge(tmp_dir):
    x_train = np.random.rand(100, 33)
    y_train = np.random.rand(100, 1)

    input_node1 = ak.Input()
    input_node2 = ak.Input()
    output_node1 = ak.DenseBlock()(input_node1)
    output_node2 = ak.DenseBlock()(input_node2)
    output_node = ak.Merge()([output_node1, output_node2])
    output_node = ak.RegressionHead()(output_node)

    graph = ak.GraphAutoModel([input_node1, input_node2],
                              output_node,
                              directory=tmp_dir,
                              max_trials=1)
    graph.fit([x_train, x_train], y_train,
              epochs=1,
              batch_size=100,
              verbose=False,
              validation_split=0.5)
    result = graph.predict([x_train, x_train])

    assert result.shape == (100, 1)

def test_preprocessing(_, tmp_dir):
    x_train = np.random.rand(100, 33)
    y_train = np.random.rand(100, 1)

    input_node1 = ak.Input()
    temp_node1 = ak.Normalization()(input_node1)
    output_node1 = ak.DenseBlock()(temp_node1)

    output_node3 = ak.Normalization()(temp_node1)
    output_node3 = ak.DenseBlock()(output_node3)

    input_node2 = ak.Input()
    output_node2 = ak.Normalization()(input_node2)
    output_node2 = ak.DenseBlock()(output_node2)

    output_node = ak.Merge()([output_node1, output_node2, output_node3])
    output_node = ak.RegressionHead()(output_node)

    graph = ak.GraphAutoModel([input_node1, input_node2],
                              output_node,
                              directory=tmp_dir,
                              max_trials=1)
    graph.fit([x_train, x_train], y_train,
              epochs=1,
              batch_size=100,
              validation_data=([x_train, x_train], y_train),
              validation_split=0.5,
              verbose=False)

def test_hyper_graph_cycle(tmp_dir):
    input_node1 = ak.Input()
    input_node2 = ak.Input()
    output_node1 = ak.DenseBlock()(input_node1)
    output_node2 = ak.DenseBlock()(input_node2)
    output_node = ak.Merge()([output_node1, output_node2])
    head = ak.RegressionHead()
    output_node = head(output_node)
    head.outputs = output_node1

    with pytest.raises(ValueError) as info:
        ak.GraphAutoModel([input_node1, input_node2],
                          output_node,
                          directory=tmp_dir)
    assert str(info.value) == 'The network has a cycle.'

def test_input_missing():
    input_node1 = ak.Input()
    input_node2 = ak.Input()
    output_node1 = ak.DenseBlock()(input_node1)
    output_node2 = ak.DenseBlock()(input_node2)
    output_node = ak.Merge()([output_node1, output_node2])
    output_node = ak.RegressionHead()(output_node)

    with pytest.raises(ValueError) as info:
        ak.hypermodel.graph.GraphHyperModel(input_node1, output_node)
    assert 'A required input is missing for HyperModel' in str(info.value)

def test_hyper_graph_cycle():
    input_node1 = ak.Input()
    input_node2 = ak.Input()
    output_node1 = ak.DenseBlock()(input_node1)
    output_node2 = ak.DenseBlock()(input_node2)
    output_node = ak.Merge()([output_node1, output_node2])
    head = ak.RegressionHead()
    output_node = head(output_node)
    head.outputs = output_node1

    with pytest.raises(ValueError) as info:
        ak.hypermodel.graph.GraphHyperModel([input_node1, input_node2],
                                            output_node)
    assert 'The network has a cycle.' in str(info.value)

def test_input_missing(tmp_dir):
    input_node1 = ak.Input()
    input_node2 = ak.Input()
    output_node1 = ak.DenseBlock()(input_node1)
    output_node2 = ak.DenseBlock()(input_node2)
    output_node = ak.Merge()([output_node1, output_node2])
    output_node = ak.RegressionHead()(output_node)

    with pytest.raises(ValueError) as info:
        ak.GraphAutoModel(input_node1, output_node, directory=tmp_dir)
    assert str(info.value).startswith('A required input is missing for HyperModel')

x_image = x_train.reshape(x_train.shape + (1,))
x_test = x_test.reshape(x_test.shape + (1,))

x_structured = np.random.rand(x_train.shape[0], 100)
y_regression = np.random.rand(x_train.shape[0], 1)
y_classification = y_classification.reshape(-1, 1)

# Build model and train.
inputs = ak.ImageInput(shape=(28, 28, 1))
outputs1 = ak.ResNetBlock(version='next')(inputs)
outputs2 = ak.XceptionBlock()(inputs)
image_outputs = ak.Merge()((outputs1, outputs2))

structured_inputs = ak.StructuredDataInput()
structured_outputs = ak.DenseBlock()(structured_inputs)
merged_outputs = ak.Merge()((structured_outputs, image_outputs))

classification_outputs = ak.ClassificationHead()(merged_outputs)
regression_outputs = ak.RegressionHead()(merged_outputs)
automodel = ak.GraphAutoModel(inputs=[inputs, structured_inputs],
                              outputs=[regression_outputs,
                                       classification_outputs])

automodel.fit((x_image, x_structured),
              (y_regression, y_classification),
              # trials=100,
              validation_split=0.2,
              epochs=200,
              callbacks=[tf.keras.callbacks.EarlyStopping()])

x_train = x_train[:data_slice]
y_classification = y_classification[:data_slice]
x_test = x_test[:data_slice]
y_test = y_test[:data_slice]
x_image = x_train.reshape(x_train.shape + (1,))
x_test = x_test.reshape(x_test.shape + (1,))

x_structured = np.random.rand(x_train.shape[0], 100)
y_regression = np.random.rand(x_train.shape[0], 1)
y_classification = y_classification.reshape(-1, 1)

# Build model and train.
inputs = ak.ImageInput(shape=(28, 28, 1))
outputs1 = ak.ResNetBlock(version='next')(inputs)
outputs2 = ak.XceptionBlock()(inputs)
image_outputs = ak.Merge()((outputs1, outputs2))

structured_inputs = ak.StructuredDataInput()
structured_outputs = ak.DenseBlock()(structured_inputs)
merged_outputs = ak.Merge()((structured_outputs, image_outputs))

classification_outputs = ak.ClassificationHead()(merged_outputs)
regression_outputs = ak.RegressionHead()(merged_outputs)
automodel = ak.GraphAutoModel(inputs=[inputs, structured_inputs],
                              outputs=[regression_outputs,
                                       classification_outputs])

automodel.fit((x_image, x_structured),
              (y_regression, y_classification),
              # trials=100,
              validation_split=0.2,
              epochs=200,