I'm trying to implement a CycleGAN in Keras and when trying to translate a base image without training I get this error, which adds a None to the Input shape of my Generator. I get the same results with generatorAtoB.predict(), so that isn't the problem. Here's the code for the architecture I'm trying to implement. X2[0] is just a numpy array with shapes (256, 256, 3), which is mentioned in the input shape of my function. Here's the error log and the code I'm using.

EDIT

I found the error, keras expects a batch size as the first dimension, so reshaping my array to (1, 256, 256, 3) solves it.

Error Log

ValueError: Input 0 is incompatible with layer model_7: expected shape=(None, 256, 256, 3), found shape=(256, 256, 3)

Model architecture

# residual block for the generator
def res_block(filters, inputs):
    # kernel weights initializer
    init = RandomNormal(stddev=0.02)
    x = Conv2D(filters, 3, padding='same', kernel_initializer=init)(inputs)
    x = InstanceNormalization(axis=-1)(x)
    x = Activation('selu')(x)
    x = Conv2D(filters, 3, padding='same', kernel_initializer=init)(x)
    x = InstanceNormalization(axis=-1)(x)
    # concatenate second conv layer with the inputs
    x = Concatenate()([x, inputs])
    return x

# generator function
def generator(img_shape = (256, 256, 3), n_blocks = 6):
    # weight initialization
    init = RandomNormal(stddev=0.02)
    inputs = Input(shape = img_shape)
    x = Conv2D(16, 5, padding='same', kernel_initializer=init)(inputs)
    x = InstanceNormalization(axis=-1)(x)
    x = Activation('selu')(x)
    
    x = Conv2D(32, 3, 2, padding='same', kernel_initializer=init)(x)
    x = InstanceNormalization(axis=-1)(x)
    x = Activation('selu')(x)
    
    x = Conv2D(64, 3, 2, padding='same', kernel_initializer=init)(x)
    x = InstanceNormalization(axis=-1)(x)
    x = Activation('selu')(x)
    
    # add residual blocks to our generator
    for _ in range(n_blocks):
        x = res_block(128, x)
    
    # transpose convolutions
    x = Conv2DTranspose(32, 3, strides = 2, padding='same', kernel_initializer=init)(x)
    x = InstanceNormalization(axis=-1)(x)
    x = Activation('selu')(x)
    
    x = Conv2DTranspose(64, 3, 2, padding='same', kernel_initializer=init)(x)
    x = InstanceNormalization(axis=-1)(x)
    x = Activation('selu')(x)
    
    # output layer
    x = Conv2D(3, 7, padding='same', kernel_initializer=init)(x)
    x = InstanceNormalization(axis=-1)(x)
    outputs = Activation('tanh')(x)
    
    # create the model
    model = Model(inputs, outputs)
    return model

# predicting the target to a base image
IMG_SHAPE = (256, 256, 3)
generator_AtoB = generator(IMG_SHAPE)
generator_AtoB(X2[0])