ValueError with complex_conv3d_1

[TeleRagingFires]

I am now trying to use Keras-complex on an autoencoder for one image compression and reconstruction project.
In my code:

**def encoder(x):
    x = complexnn.conv.ComplexConv3D(filters=2, kernel_size=(3, 3, 2), padding='same', data_format='channels_first',
                                     input_shape=(1, 32, 32, 2))(x)**

as the first layer of my model, where x is predefined with
**image_tensor = Input(shape=(img_channels, img_height, img_width, img_RI))**
The Error report I got：
ValueError: Input 0 is incompatible with layer complex_conv3d_1: expected axis 1 of input shape to have value 0 but got shape (None, 1, 32, 32, 2)