How to show the output image of a cnn

Question

Im working on a project for uni and I am completly stuck at a problem. I want to train a cnn model to do image style transfer from one picture to another and I looked it up in this toutorial: https://www.tensorflow.org/tutorials/generative/style_transfer#learn_more but I don't want to train just one image but I have to train it on one style and then put a video in, so that each picture is converted to this style. So I have to put my pictures in the trained model and I can't get the output right to show me a image.

I worked on said toutorial and after I trained the Model I tried to put a new image in the model. like this:

image = load_img('Tests\hut.jpeg')

def show_processed_image(image):
    outputs = extractor(image)
    generated_image = outputs['content']['block5_conv2'] 
    print(generated_image)
    tensor_to_image(generated_image)
    plt.show()

show_processed_image(image)

The extractor is the traindes model, it looks like this:

class StyleContentModel(tf.keras.models.Model):
  def __init__(self, style_layers, content_layers):
    super(StyleContentModel, self).__init__()
    self.vgg = vgg_layers(style_layers + content_layers)
    self.style_layers = style_layers
    self.content_layers = content_layers
    self.num_style_layers = len(style_layers)
    self.vgg.trainable = False

  def call(self, inputs):
    "Expects float input in [0,1]"
    inputs = inputs*255.0
    preprocessed_input = tf.keras.applications.vgg19.preprocess_input(inputs)
    outputs = self.vgg(preprocessed_input)
    style_outputs, content_outputs = (outputs[:self.num_style_layers],
                                      outputs[self.num_style_layers:])

    style_outputs = [gram_matrix(style_output)
                     for style_output in style_outputs]

    content_dict = {content_name: value
                    for content_name, value
                    in zip(self.content_layers, content_outputs)}

    style_dict = {style_name: value
                  for style_name, value
                  in zip(self.style_layers, style_outputs)}

    return {'content': content_dict, 'style': style_dict}